ai-muninn

ai-muninn https://ai-muninn.com/en/blog Notes on AI inference infrastructure: DGX Spark, vLLM, local AI agents. Sun, 06 Sep 2026 17:04:26 GMT https://validator.w3.org/feed/docs/rss2.html https://github.com/jpmonette/feed en 2026 coolthor <![CDATA[[Benchmark] Qwen3.8-Flash-Next NVFP4 on a DGX Spark: 41.7 tok/s, RAM for Traffic, Disk for the Dictionary]]> https://ai-muninn.com/en/blog/qwen38-flash-next-nvfp4-dgx-spark-vllm-recipe https://ai-muninn.com/en/blog/qwen38-flash-next-nvfp4-dgx-spark-vllm-recipe Sun, 06 Sep 2026 00:00:00 GMT DGX Spark GB10 vLLM NVFP4 MTP Qwen3.8 <![CDATA[[Benchmark] Two characters in one shot: MiniMax-H3 Ref2VA takes multiple reference images]]> https://ai-muninn.com/en/blog/minimax-h3-ref2va-two-characters https://ai-muninn.com/en/blog/minimax-h3-ref2va-two-characters Sun, 06 Sep 2026 00:00:00 GMT MiniMax-H3 Ref2VA ComfyUI RTX 5090 AI video <![CDATA[[Benchmark] From OOM to 8.6 minutes: a MiniMax-H3 config stack for one RTX 5090]]> https://ai-muninn.com/en/blog/minimax-h3-rtx5090-config-stack https://ai-muninn.com/en/blog/minimax-h3-rtx5090-config-stack Thu, 03 Sep 2026 00:00:00 GMT MiniMax-H3 RTX 5090 ComfyUI NVFP4 video generation <![CDATA[[Dev Workflow] AI Slop Is Structural: 93.2% Detectable With Every Style Tell Stripped]]> https://ai-muninn.com/en/blog/ai-slop-is-structural https://ai-muninn.com/en/blog/ai-slop-is-structural Mon, 31 Aug 2026 00:00:00 GMT AI writing blog workflow Claude Code skill StoryScope <![CDATA[[Benchmark] Ten effect embeddings for MiniMax-H3 — 10 MB that buys you bullet time, fire breath and a full year of seasons]]> https://ai-muninn.com/en/blog/minimax-h3-effect-embeddings-rtx5090 https://ai-muninn.com/en/blog/minimax-h3-effect-embeddings-rtx5090 Mon, 31 Aug 2026 00:00:00 GMT MiniMax-H3 ComfyUI RTX 5090 video generation embeddings <![CDATA[[Benchmark] GLM-5.3-Flash 320B on One DGX Spark: 15.4 tok/s with Vision Working]]> https://ai-muninn.com/en/blog/glm53-flash-one-dgx-spark https://ai-muninn.com/en/blog/glm53-flash-one-dgx-spark Sun, 30 Aug 2026 00:00:00 GMT DGX Spark GB10 GLM-5.3 llama.cpp multimodal speculative decoding <![CDATA[[Benchmark] A 177B MoE at Full 262K Context on a DGX Spark: 76.65 tok/s on a File Edit]]> https://ai-muninn.com/en/blog/qwen4exp-dgx-spark-262k-no-tradeoff https://ai-muninn.com/en/blog/qwen4exp-dgx-spark-262k-no-tradeoff Fri, 28 Aug 2026 00:00:00 GMT DGX Spark GB10 llama.cpp MoE long context <![CDATA[[Benchmark] A 177B MoE on Three Modded 2080 Tis: 23 tok/s at 128K, 77 on a File Edit]]> https://ai-muninn.com/en/blog/qwen4exp-177b-three-2080ti https://ai-muninn.com/en/blog/qwen4exp-177b-three-2080ti Fri, 28 Aug 2026 00:00:00 GMT llama.cpp 2080 Ti MoE speculative decoding quantization <![CDATA[[Benchmark] Qwen3.8-27B hits 65 tok/s on one DGX Spark — 12.3 without speculative decoding]]> https://ai-muninn.com/en/blog/dgx-spark-bandwidth-ceiling-85-percent https://ai-muninn.com/en/blog/dgx-spark-bandwidth-ceiling-85-percent Sun, 23 Aug 2026 00:00:00 GMT DGX Spark GB10 SM121 NVFP4 Qwen3.8-27B SGLang speculative decoding DFlash2 DSpark MTP memory bandwidth benchmark <![CDATA[[Benchmark] Fixing NCCL's Stub-Library Error Cut PCIe Traffic 99% and Barely Moved Speed]]> https://ai-muninn.com/en/blog/nccl-2080ti-stub-library-fix https://ai-muninn.com/en/blog/nccl-2080ti-stub-library-fix Sun, 23 Aug 2026 00:00:00 GMT NCCL llama.cpp tensor parallel 2080 Ti CUDA <![CDATA[[Benchmark] Dual-GPU AllReduce Only Uses 8% of PCIe Gen3 x16 — It Moves Little, Very Often]]> https://ai-muninn.com/en/blog/pcie-allreduce-dual-2080ti https://ai-muninn.com/en/blog/pcie-allreduce-dual-2080ti Sun, 23 Aug 2026 00:00:00 GMT llama.cpp tensor parallel PCIe NVLink 2080 Ti <![CDATA[[Benchmark] MiniMax-H3 1080p Isn't Unsupported, It's Three and a Half Hours]]> https://ai-muninn.com/en/blog/minimax-h3-rtx5090-character-lock https://ai-muninn.com/en/blog/minimax-h3-rtx5090-character-lock Sun, 23 Aug 2026 00:00:00 GMT MiniMax-H3 RTX 5090 z-image character consistency ComfyUI <![CDATA[[Benchmark] Two Modded 2080 Tis Reach 59.6 tok/s on Qwen3.8-27B With llama.cpp Tensor Parallel]]> https://ai-muninn.com/en/blog/qwen38-dual-2080ti-tensor-parallel https://ai-muninn.com/en/blog/qwen38-dual-2080ti-tensor-parallel Sat, 22 Aug 2026 00:00:00 GMT llama.cpp tensor parallel 2080 Ti Qwen3.8 MTP <![CDATA[[AI Agent] From 41 Minutes to 73 Seconds: Why My Coding Agent's Small Tickets Were So Slow]]> https://ai-muninn.com/en/blog/agent-ticket-41min-to-73s https://ai-muninn.com/en/blog/agent-ticket-41min-to-73s Fri, 21 Aug 2026 00:00:00 GMT AI Agent Claude Code Codex agent orchestration <![CDATA[[Benchmark] Free 15% Speedup on a 2080 Ti: One Broken Chat Template, One Starving MTP Head]]> https://ai-muninn.com/en/blog/chat-template-kv-mtp-free-speedup https://ai-muninn.com/en/blog/chat-template-kv-mtp-free-speedup Fri, 21 Aug 2026 00:00:00 GMT llama.cpp chat template KV cache MTP speculative decoding 2080 Ti Qwen3.8 <![CDATA[[Just for Fun — Advanced] Why Isn't Your 4-Bit Quant Faster on a 2080 Ti? I Tore Open the CUDA Backend to Find Out]]> https://ai-muninn.com/en/blog/why-4bit-isnt-faster-on-2080ti https://ai-muninn.com/en/blog/why-4bit-isnt-faster-on-2080ti Thu, 20 Aug 2026 00:00:00 GMT 2080 Ti Turing quantization GGUF AWQ Marlin INT8 W4A8 benchmark <![CDATA[[Junk-Tier Big Models #5] Qwen3.8-27B on a 2018 22GB card: 30 tok/s, and it one-shot a 3D scene]]> https://ai-muninn.com/en/blog/qwen38-27b-ud-on-one-2080ti https://ai-muninn.com/en/blog/qwen38-27b-ud-on-one-2080ti Tue, 18 Aug 2026 00:00:00 GMT Qwen3.8 unsloth 2080 Ti llama.cpp GGUF local LLM MTP <![CDATA[[Announcement] On hiatus until August 21]]> https://ai-muninn.com/en/blog/back-after-acute-cholecystitis https://ai-muninn.com/en/blog/back-after-acute-cholecystitis Sat, 15 Aug 2026 00:00:00 GMT Announcement <![CDATA[[Benchmark] Running MiniMax-H3 on a DGX Spark — and why NVIDIA VSR is off the table for now]]> https://ai-muninn.com/en/blog/dgx-spark-minimax-h3-span-upscaler https://ai-muninn.com/en/blog/dgx-spark-minimax-h3-span-upscaler Fri, 07 Aug 2026 00:00:00 GMT DGX Spark GB10 MiniMax-H3 ComfyUI SPAN aarch64 SageAttention <![CDATA[[Just for Fun — Advanced] Wait, a 2080 Ti Can Run MiniMax-H3? 1080p With Audio on a 2018 Card]]> https://ai-muninn.com/en/blog/minimax-h3-on-modded-2080ti-22gb https://ai-muninn.com/en/blog/minimax-h3-on-modded-2080ti-22gb Thu, 06 Aug 2026 00:00:00 GMT 2080 Ti Turing MiniMax-H3 ComfyUI SageAttention quantization benchmark <![CDATA[[Benchmark] Twice as Fast: MiniMax-H3 on an RTX 5090, 625s Down to 314s]]> https://ai-muninn.com/en/blog/minimax-h3-rtx5090-speedup-vsr https://ai-muninn.com/en/blog/minimax-h3-rtx5090-speedup-vsr Thu, 06 Aug 2026 00:00:00 GMT MiniMax-H3 RTX 5090 ComfyUI RTX Video Super Resolution SageAttention Real-ESRGAN <![CDATA[[Benchmark] Running MiniMax-H3 on one RTX 5090: four files, 31.7 GB, 175s per talking clip]]> https://ai-muninn.com/en/blog/minimax-h3-nvfp4-rtx5090 https://ai-muninn.com/en/blog/minimax-h3-nvfp4-rtx5090 Tue, 04 Aug 2026 00:00:00 GMT MiniMax-H3 NVFP4 RTX 5090 ComfyUI text-to-video quantization <![CDATA[[DeepSeek-V4-Flash] A frontier-class open model on hardware you own: running DeepSeek-V4-Flash-0731 on a DGX Spark]]> https://ai-muninn.com/en/blog/ds4-0731-on-dgx-spark-howto https://ai-muninn.com/en/blog/ds4-0731-on-dgx-spark-howto Sun, 02 Aug 2026 00:00:00 GMT DeepSeek-V4-Flash 0731 DGX Spark GB10 llama.cpp CUDA unified memory local LLM tutorial <![CDATA[[Junk-Tier Big Models #4] A frontier-class open model on hardware you already own: DeepSeek-V4-Flash-0731 on one 22GB 2080 Ti]]> https://ai-muninn.com/en/blog/ds4-0731-on-one-2080ti-howto https://ai-muninn.com/en/blog/ds4-0731-on-one-2080ti-howto Sun, 02 Aug 2026 00:00:00 GMT DeepSeek-V4-Flash 0731 MoE 2080 Ti llama.cpp expert offload local LLM tutorial <![CDATA[[Dev Workflow] My Skill Had the Check Written Perfectly — It Just Never Ran]]> https://ai-muninn.com/en/blog/ai-tic-check-that-never-ran https://ai-muninn.com/en/blog/ai-tic-check-that-never-ran Wed, 29 Jul 2026 00:00:00 GMT AI writing de-AI writing workflow Claude Code editing quality gates LLM <![CDATA[[Junk-Tier Big Models #3] A 284B MoE on ONE 2080 Ti — and it beats my DGX Spark]]> https://ai-muninn.com/en/blog/deepseek-v4-flash-284b-on-one-2080ti https://ai-muninn.com/en/blog/deepseek-v4-flash-284b-on-one-2080ti Wed, 29 Jul 2026 00:00:00 GMT DeepSeek-V4-Flash MoE 2080 Ti llama.cpp expert offload MTP speculative decoding DGX Spark local LLM <![CDATA[[Dev Workflow] Agent Memory Self-Poisoning: When an AI Agent Trusts Its Own Wrong Answers]]> https://ai-muninn.com/en/blog/agent-memory-self-poisoning https://ai-muninn.com/en/blog/agent-memory-self-poisoning Mon, 27 Jul 2026 00:00:00 GMT AI agent agent memory Hermes RAG LLM <![CDATA[[DeepSeek-V4-Flash] The Engine Upgrade That OOM'd My DGX Spark — and Why I Rolled It Back]]> https://ai-muninn.com/en/blog/hikari-ds4-oom-rollback https://ai-muninn.com/en/blog/hikari-ds4-oom-rollback Sat, 25 Jul 2026 00:00:00 GMT DeepSeek-V4-Flash DGX Spark ds4 OOM Entrpi KV cache benchmark <![CDATA[[LLM Deep Dive] Surgical GGUF Quantization: Quantize Only the Tensors You Choose]]> https://ai-muninn.com/en/blog/layer-aware-gguf-quantization https://ai-muninn.com/en/blog/layer-aware-gguf-quantization Thu, 23 Jul 2026 00:00:00 GMT quantization GGUF llama.cpp llama-quantize tensor-type mixed precision Laguna LLM Deep Dive <![CDATA[[LLM Deep Dive] The Best Free Open-Source Model for a Single 24GB GPU? My Pick Is ThinkingCap-Qwen3.6-27B]]> https://ai-muninn.com/en/blog/thinkingcap-qwen36-27b-local-brain https://ai-muninn.com/en/blog/thinkingcap-qwen36-27b-local-brain Wed, 22 Jul 2026 00:00:00 GMT Qwen3.6 ThinkingCap abliterated local LLM llama.cpp 2080 Ti efficient thinking MTP reasoning model <![CDATA[[Junk-Tier Big Models #2] Running Poolside Laguna S 2.1, a 118B Coding MoE, on ONE 22GB 2080 Ti]]> https://ai-muninn.com/en/blog/laguna-118b-moe-on-one-2080ti https://ai-muninn.com/en/blog/laguna-118b-moe-on-one-2080ti Wed, 22 Jul 2026 00:00:00 GMT Laguna Poolside MoE 2080 Ti llama.cpp DFlash speculative decoding local LLM quantization <![CDATA[[Agent 101 #16] Hermes config health check: 5 silent gotchas that make your assistant act weird]]> https://ai-muninn.com/en/blog/hermes-config-gotchas https://ai-muninn.com/en/blog/hermes-config-gotchas Tue, 21 Jul 2026 00:00:00 GMT AI assistant AI agent Hermes config debugging self-hosted <![CDATA[[DeepSeek-V4-Flash] Swapping the ds4 Engine for a Free Half-Generation Speedup on One DGX Spark]]> https://ai-muninn.com/en/blog/ds4-entrpi-engine-swap https://ai-muninn.com/en/blog/ds4-entrpi-engine-swap Tue, 21 Jul 2026 00:00:00 GMT DeepSeek-V4-Flash DGX Spark ds4 speculative decoding KV cache benchmark <![CDATA[[Junk-Tier Big Models #1] Running a 119B MoE at 74 tok/s on Three 2080 Tis]]> https://ai-muninn.com/en/blog/run-119b-moe-on-3x-2080ti https://ai-muninn.com/en/blog/run-119b-moe-on-3x-2080ti Tue, 21 Jul 2026 00:00:00 GMT llama.cpp MoE expert offload 2080 Ti EPYC quantization benchmark <![CDATA[[Just for Fun — Advanced] Two Identical 2080 Tis, One 3.4× Slower — the Culprit Was a Single dtype Log Line]]> https://ai-muninn.com/en/blog/2080ti-turing-fp32-fallback https://ai-muninn.com/en/blog/2080ti-turing-fp32-fallback Sat, 18 Jul 2026 00:00:00 GMT 2080 Ti Turing ComfyUI Z-Image quantization GPU benchmark dev workflow <![CDATA[[Dev Workflow] Your AI Agent's Skills Are a Context Budget: Cutting 193 to 7]]> https://ai-muninn.com/en/blog/slimming-the-agent-skill-budget https://ai-muninn.com/en/blog/slimming-the-agent-skill-budget Fri, 17 Jul 2026 00:00:00 GMT Dev Workflow AI agent Claude Code Codex skills context engineering governance <![CDATA[[Dev Workflow] The Two Axes That Let a Fleet of AIs Collaborate Without Re-Explaining]]> https://ai-muninn.com/en/blog/how-ai-agents-collaborate-without-re-explaining https://ai-muninn.com/en/blog/how-ai-agents-collaborate-without-re-explaining Thu, 16 Jul 2026 00:00:00 GMT Dev Workflow AI agent multi-agent handoff knowledge base Claude Code Codex governance <![CDATA[[Dev Workflow] Why an AI Agent's Memory Needs a Distilled Layer Above Search]]> https://ai-muninn.com/en/blog/why-agent-memory-needs-a-distilled-layer https://ai-muninn.com/en/blog/why-agent-memory-needs-a-distilled-layer Wed, 15 Jul 2026 00:00:00 GMT Dev Workflow AI agent memory knowledge base distillation RAG Claude Code governance <![CDATA[[Dev Workflow] From Markdown Search to a Knowledge Graph: How My AI's Memory Grew a Second Layer]]> https://ai-muninn.com/en/blog/from-markdown-search-to-knowledge-graph https://ai-muninn.com/en/blog/from-markdown-search-to-knowledge-graph Tue, 14 Jul 2026 00:00:00 GMT Dev Workflow knowledge graph AI agent memory qmd musubi Claude Code RAG <![CDATA[[Dev Workflow] Retiring an AI Agent's Memory System: Three Traps When Doctrine Drifts From Runtime]]> https://ai-muninn.com/en/blog/retiring-ai-agent-memory-system https://ai-muninn.com/en/blog/retiring-ai-agent-memory-system Sun, 12 Jul 2026 00:00:00 GMT AI agent knowledge base memory dev workflow Syncthing governance <![CDATA[[Dev Workflow] Delegating to an AI Coding Agent: The Unit of Work Is a Ticket File, Not a Conversation]]> https://ai-muninn.com/en/blog/dispatch-tickets-not-conversations https://ai-muninn.com/en/blog/dispatch-tickets-not-conversations Sun, 12 Jul 2026 00:00:00 GMT Codex Claude Code AI agent dev workflow delegation orchestration <![CDATA[[Dev Workflow] When Your Quota Runs Out Mid-Task: A Live-State Handoff Protocol for Claude Code and Codex]]> https://ai-muninn.com/en/blog/claude-code-codex-handoff-protocol https://ai-muninn.com/en/blog/claude-code-codex-handoff-protocol Sat, 11 Jul 2026 00:00:00 GMT Claude Code Codex AI agent dev workflow handoff hooks <![CDATA[[Just for Fun — Advanced] 0xc0000409: When My AI Service Died Silently and the Log Ate the Evidence]]> https://ai-muninn.com/en/blog/0xc0000409-crash-detective-2080ti https://ai-muninn.com/en/blog/0xc0000409-crash-detective-2080ti Fri, 10 Jul 2026 00:00:00 GMT local LLM llama.cpp Windows crash forensics observability 0xc0000409 <![CDATA[[Local LLM] How to tell if a hyped LLM optimization is real on your hardware: read the source, find the ceiling, run one experiment]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-evaluating-optimization-claims https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-evaluating-optimization-claims Fri, 10 Jul 2026 00:00:00 GMT DGX Spark GB10 DeepSeek-V4-Flash methodology local LLM verification <![CDATA[Hermes Agent: The Complete Self-Hosted Guide — Desktop Install to a Local-Model Fleet]]> https://ai-muninn.com/en/blog/hermes-agent-complete-guide https://ai-muninn.com/en/blog/hermes-agent-complete-guide Fri, 10 Jul 2026 00:00:00 GMT Hermes AI agent self-hosted ChatGPT OAuth Telegram local LLM MCP <![CDATA[[Local LLM] FlashMemory can't improve DeepSeek-V4-Flash's own lightning indexer — I retrained it on my exact Q2 and it still lost]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-flashmemory-vs-native-indexer https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-flashmemory-vs-native-indexer Thu, 09 Jul 2026 00:00:00 GMT DGX Spark GB10 DeepSeek-V4-Flash KV cache sparse attention ds4 local LLM <![CDATA[DGX Spark in 2026: What Still Works, What Broke, and What I'd Run Today]]> https://ai-muninn.com/en/blog/dgx-spark-2026-current-guide https://ai-muninn.com/en/blog/dgx-spark-2026-current-guide Tue, 07 Jul 2026 00:00:00 GMT DGX Spark GB10 Gemma 4 vLLM NVFP4 MTP Ollama local LLM 2026 guide <![CDATA[[Local LLM] Why a 284B fits a 128GB GB10 at long context: DeepSeek-V4-Flash attacks the KV cache, not the parameter count]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-architecture https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-architecture Tue, 07 Jul 2026 00:00:00 GMT DGX Spark GB10 DeepSeek-V4-Flash KV cache sparse attention ds4 local LLM <![CDATA[How to Run an AI Agent from Your Own Desktop: ChatGPT OAuth, Telegram, LINE, and Local Models]]> https://ai-muninn.com/en/blog/run-ai-agent-from-your-desktop https://ai-muninn.com/en/blog/run-ai-agent-from-your-desktop Tue, 07 Jul 2026 00:00:00 GMT AI agent self-hosted ChatGPT OAuth openclaw Hermes Telegram LINE local LLM <![CDATA[[Local LLM] Depth-1 MTP on V4-Flash: +9% on agent turns, −4% on prose — route speculative decode by workload]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-mtp-workload-asymmetry https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-mtp-workload-asymmetry Mon, 06 Jul 2026 00:00:00 GMT DGX Spark GB10 DeepSeek-V4-Flash speculative decoding MTP ds4 local LLM <![CDATA[[Local LLM] My 284B agent quietly stopped reusing its KV cache — the ds4 evict storm that re-paid prefill every turn]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-kv-evict-storm https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-kv-evict-storm Sun, 05 Jul 2026 00:00:00 GMT DGX Spark GB10 DeepSeek-V4-Flash KV cache ds4 local LLM prefill agent <![CDATA[[Just for Fun — Advanced] I Doubled My Agent's Decode Speed and It Got Slower: TTFT Is the Number You Actually Feel]]> https://ai-muninn.com/en/blog/why-30-toks-feels-slower-than-14-ttft https://ai-muninn.com/en/blog/why-30-toks-feels-slower-than-14-ttft Fri, 03 Jul 2026 00:00:00 GMT local LLM AI agent TTFT llama.cpp Qwen3 KV cache <![CDATA[[Just for Fun — Advanced] Progressive Streaming on a Slow Model Got My Bot Rate-Limited by Telegram]]> https://ai-muninn.com/en/blog/telegram-streaming-flood-control-slow-llm https://ai-muninn.com/en/blog/telegram-streaming-flood-control-slow-llm Thu, 02 Jul 2026 00:00:00 GMT local LLM AI agent Telegram streaming rate limit llama.cpp <![CDATA[[Agent 101 #15] Hermes /learn: I had a local 27B write its own reusable skill]]> https://ai-muninn.com/en/blog/hermes-learn-self-authored-skills https://ai-muninn.com/en/blog/hermes-learn-self-authored-skills Wed, 01 Jul 2026 00:00:00 GMT AI assistant AI agent Hermes skills /learn local model Kanban advanced <![CDATA[[Agent 101 #14] One spec, three assistants, three Tetris games: a Hermes Kanban dispatch test]]> https://ai-muninn.com/en/blog/hermes-project-three-sibs-tetris https://ai-muninn.com/en/blog/hermes-project-three-sibs-tetris Mon, 29 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes dispatch Kanban local model Tetris <![CDATA[[Troubleshooting] HuggingFace download stuck at 0 bytes on Windows — Xet, Python 3.13, ai-toolkit]]> https://ai-muninn.com/en/blog/huggingface-download-stuck-zero-bytes-windows-ai-toolkit https://ai-muninn.com/en/blog/huggingface-download-stuck-zero-bytes-windows-ai-toolkit Mon, 29 Jun 2026 00:00:00 GMT Troubleshooting HuggingFace Windows ai-toolkit RTX 5090 <![CDATA[[LoRA] The character-LoRA control panel: dialing in style, realism, and identity]]> https://ai-muninn.com/en/blog/character-lora-control-panel-wan22 https://ai-muninn.com/en/blog/character-lora-control-panel-wan22 Sun, 28 Jun 2026 00:00:00 GMT LoRA Wan 2.2 ComfyUI AI character local generation <![CDATA[[Just for Fun — Advanced] The Tool-Definition Tax: 17K Tokens Before I Say a Word, Re-Billed on Every Cache Miss]]> https://ai-muninn.com/en/blog/tool-definition-tax-17k-context-economics https://ai-muninn.com/en/blog/tool-definition-tax-17k-context-economics Sat, 27 Jun 2026 00:00:00 GMT local LLM AI agent context llama.cpp Qwen3 tool calling <![CDATA[[Just for Fun — Advanced] llama.cpp won't persist KV cache to disk — so I put a 60-line proxy in front of it (7× faster restore)]]> https://ai-muninn.com/en/blog/kv-cache-disk-restore-7x https://ai-muninn.com/en/blog/kv-cache-disk-restore-7x Fri, 26 Jun 2026 00:00:00 GMT local LLM llama.cpp KV cache TTFT Qwen3 prefill <![CDATA[[Just for Fun — Advanced] Quantizing the Draft Cache Backfired — A Counterintuitive Look at Qwen MTP (f16 ran 34% faster than q4)]]> https://ai-muninn.com/en/blog/mtp-quantized-draft-cache-backfires https://ai-muninn.com/en/blog/mtp-quantized-draft-cache-backfires Thu, 25 Jun 2026 00:00:00 GMT MTP speculative decoding local LLM Qwen3 llama.cpp KV cache <![CDATA[[Agent 101 #13] See what your fleet of AI agents is doing — from your phone: Muninn adds a Kanban board]]> https://ai-muninn.com/en/blog/muninn-kanban-board https://ai-muninn.com/en/blog/muninn-kanban-board Wed, 24 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes Muninn Kanban iOS phone <![CDATA[[Just for Fun — Advanced] I Maxed Context to 256K, It Loaded Fine — Then Crashed in Real Use: A VRAM Detective Story on a 22GB Frankencard]]> https://ai-muninn.com/en/blog/context-vs-vram-256k-oom-2080ti https://ai-muninn.com/en/blog/context-vs-vram-256k-oom-2080ti Wed, 24 Jun 2026 00:00:00 GMT local LLM llama.cpp Qwen3 VRAM context window KV cache <![CDATA[[Agent 101 #12] Reach your home AI agent from anywhere: Muninn, a private iOS app over iroh P2P]]> https://ai-muninn.com/en/blog/hermes-muninn-phone-bridge https://ai-muninn.com/en/blog/hermes-muninn-phone-bridge Tue, 23 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes iroh P2P iOS phone bridge <![CDATA[[Just for Fun — Advanced] I Gave Up 100 tok/s for 30 — Fast Isn't the Same as Useful]]> https://ai-muninn.com/en/blog/gemma-12b-vs-qwen-27b-agentic-discipline https://ai-muninn.com/en/blog/gemma-12b-vs-qwen-27b-agentic-discipline Tue, 23 Jun 2026 00:00:00 GMT local LLM AI agent Qwen3 Gemma llama.cpp kanban <![CDATA[[Agent 101 #11] Assistant gone haywire? Don't blame the engine — usually it's the car that broke, not the engine]]> https://ai-muninn.com/en/blog/hermes-harness-debugging https://ai-muninn.com/en/blog/hermes-harness-debugging Mon, 22 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes debugging harness advanced <![CDATA[[Just for Fun — Advanced] I Scored a 22GB-Modded 2080 Ti for ~$340 All-In — Just Enough to Keep a 27B Agent Running at Home]]> https://ai-muninn.com/en/blog/modded-2080ti-22gb-local-agent https://ai-muninn.com/en/blog/modded-2080ti-22gb-local-agent Mon, 22 Jun 2026 00:00:00 GMT RTX 2080 Ti GPU mod local LLM AI agent llama.cpp Qwen3 <![CDATA[Directional Steering on an Abliterated DeepSeek-V4 (DGX Spark): the same scalpel as abliteration, and why the second cut fights back]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-directional-steering https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-directional-steering Sun, 21 Jun 2026 00:00:00 GMT DeepSeek V4 directional steering activation steering abliteration representation engineering ds4 DGX Spark GB10 CUDA control vectors <![CDATA[[Agent 101 #10] Installed it, now what? Give your assistant hands — connect your own tools]]> https://ai-muninn.com/en/blog/hermes-connect-your-tools https://ai-muninn.com/en/blog/hermes-connect-your-tools Sat, 20 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes MCP tools automation getting started <![CDATA[[Agent 101 #9] Swap your assistant's brain for one on your own machine: from cloud ChatGPT to a local model]]> https://ai-muninn.com/en/blog/hermes-local-brain https://ai-muninn.com/en/blog/hermes-local-brain Fri, 19 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes local model privacy autonomy ds4 <![CDATA[[LoRA] Train your own AI character on an RTX 5090 — one image to a usable character]]> https://ai-muninn.com/en/blog/train-character-lora-wan22-rtx5090 https://ai-muninn.com/en/blog/train-character-lora-wan22-rtx5090 Thu, 18 Jun 2026 00:00:00 GMT LoRA Wan 2.2 RTX 5090 AI character local generation <![CDATA[[Agent 101 #8] One person, a whole team of assistants: each with its own desk, brain, and memory]]> https://ai-muninn.com/en/blog/hermes-multiple-sibs https://ai-muninn.com/en/blog/hermes-multiple-sibs Wed, 17 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes profiles advanced <![CDATA[[Agent 101 #7] Give your AI assistant eyes and ears: vision + voice for a text-only brain]]> https://ai-muninn.com/en/blog/hermes-agent-vision-voice https://ai-muninn.com/en/blog/hermes-agent-vision-voice Tue, 16 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes multimodal vision voice faster-whisper local model <![CDATA[[Agent 101 #6] Let your assistant run on its own: daily research that pings your Telegram]]> https://ai-muninn.com/en/blog/hermes-autonomous-daily https://ai-muninn.com/en/blog/hermes-autonomous-daily Tue, 16 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes Telegram automation scheduling getting started <![CDATA[[Agent 101 #5] Use your AI assistant from your phone: connect Hermes to Telegram]]> https://ai-muninn.com/en/blog/connect-hermes-to-telegram https://ai-muninn.com/en/blog/connect-hermes-to-telegram Tue, 16 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes Telegram getting started tutorial <![CDATA[[Agent 101 #4] How to install Hermes Agent Desktop: your first AI assistant, no terminal]]> https://ai-muninn.com/en/blog/install-hermes-desktop https://ai-muninn.com/en/blog/install-hermes-desktop Tue, 16 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes ChatGPT getting started tutorial <![CDATA[[Agent 101 #3] The fixed combo we'll use: ChatGPT as the brain, Hermes as the body]]> https://ai-muninn.com/en/blog/ai-brain-hermes-body https://ai-muninn.com/en/blog/ai-brain-hermes-body Tue, 16 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes ChatGPT getting started <![CDATA[[Agent 101 #2] What is an agent framework? Why you shouldn't roll your own — just use one that exists]]> https://ai-muninn.com/en/blog/what-is-an-agent-framework https://ai-muninn.com/en/blog/what-is-an-agent-framework Tue, 16 Jun 2026 00:00:00 GMT AI assistant AI agent Hermes getting started <![CDATA[[Agent 101 #1] AI assistant vs ChatGPT: one answers you, one uses your tools to get things done]]> https://ai-muninn.com/en/blog/ai-agent-vs-chatbot https://ai-muninn.com/en/blog/ai-agent-vs-chatbot Tue, 16 Jun 2026 00:00:00 GMT AI assistant AI agent ChatGPT getting started <![CDATA[[Just for Fun] A blog RAG support bot on a GTX 970: no torch, no vector DB, no LangChain]]> https://ai-muninn.com/en/blog/gtx-970-blog-rag-bot https://ai-muninn.com/en/blog/gtx-970-blog-rag-bot Sun, 14 Jun 2026 00:00:00 GMT Gemma 4 GTX 970 RAG llama.cpp Cloudflare Tunnel <![CDATA[[Just for Fun] On a GTX 970, Flash Attention nearly doubles long-context decode (24.3 → 42.5 tok/s)]]> https://ai-muninn.com/en/blog/gtx-970-gemma4-e2b-kv-cache-flash-attention https://ai-muninn.com/en/blog/gtx-970-gemma4-e2b-kv-cache-flash-attention Sun, 14 Jun 2026 00:00:00 GMT Gemma 4 GTX 970 Flash Attention KV cache llama.cpp <![CDATA[[vLLM] DiffusionGemma 26B NVFP4 on a DGX Spark: 158 tok/s, and why diffusion tok/s lies]]> https://ai-muninn.com/en/blog/dgx-spark-diffusiongemma-nvfp4-vllm https://ai-muninn.com/en/blog/dgx-spark-diffusiongemma-nvfp4-vllm Sat, 13 Jun 2026 00:00:00 GMT DGX Spark GB10 DiffusionGemma diffusion LLM NVFP4 vLLM local LLM <![CDATA[[Local LLM] Weights win: a 284B crushed to 2-bit still beats the small model that fits]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-284b-q2-quality https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-284b-q2-quality Fri, 12 Jun 2026 00:00:00 GMT DGX Spark GB10 DeepSeek-V4-Flash quantization Q2 asymmetric quantization local LLM ds4 <![CDATA[[Local LLM] Running a 15 tok/s 284B as your daily agent brain — the settings that make it bearable]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-context-memory-engineering https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-context-memory-engineering Fri, 12 Jun 2026 00:00:00 GMT DGX Spark GB10 DeepSeek-V4-Flash KV cache context memory ds4 local LLM <![CDATA[[Local LLM] My first Q2 model looked broken on a 128GB box — the real culprit was a parser that couldn't read DSML, not the quantization]]> https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-284b-ds4-engine https://ai-muninn.com/en/blog/dgx-spark-deepseek-v4-flash-284b-ds4-engine Fri, 12 Jun 2026 00:00:00 GMT DGX Spark GB10 DeepSeek-V4-Flash ds4 quantization Q2 tool-call DSML local LLM <![CDATA[[Benchmark] Qwen3.5-122B on DGX Spark — 2× faster]]> https://ai-muninn.com/en/blog/dgx-spark-qwen3-122b-vllm-to-atlas-2x https://ai-muninn.com/en/blog/dgx-spark-qwen3-122b-vllm-to-atlas-2x Thu, 11 Jun 2026 00:00:00 GMT Qwen3.5 DGX Spark GB10 GDN vLLM Atlas NVFP4 Benchmark SM121 <![CDATA[[Just for Fun] A GTX 970 as an offline voice assistant: Gemma 4 E2B + Piper TTS (2.8s end-to-end)]]> https://ai-muninn.com/en/blog/gtx-970-gemma4-e2b-voice-assistant https://ai-muninn.com/en/blog/gtx-970-gemma4-e2b-voice-assistant Tue, 09 Jun 2026 00:00:00 GMT Gemma 4 GTX 970 multimodal Piper TTS voice assistant <![CDATA[[Just for Fun] Gemma 4 E2B on a GTX 970: the biggest quant runs fastest (47.6 tok/s)]]> https://ai-muninn.com/en/blog/gtx-970-gemma4-e2b-quantization-benchmark https://ai-muninn.com/en/blog/gtx-970-gemma4-e2b-quantization-benchmark Tue, 09 Jun 2026 00:00:00 GMT Gemma 4 quantization GTX 970 llama.cpp benchmark <![CDATA[[Benchmark] NVFP4 Weight-Only Quantization Taxes Chinese ~2x Harder Than English (gemma-4-12B)]]> https://ai-muninn.com/en/blog/dgx-spark-nvfp4-quant-tax-chinese-vs-english https://ai-muninn.com/en/blog/dgx-spark-nvfp4-quant-tax-chinese-vs-english Fri, 05 Jun 2026 00:00:00 GMT DGX Spark GB10 Gemma 4 NVFP4 FP8 quantization MMLU TMMLU+ Traditional Chinese benchmark <![CDATA[[Benchmark] Gemma 4 12B Omni on DGX Spark: Weight-Only NVFP4 Beats W4A4 (and Keeps Multimodal)]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-12b-omni-nvfp4-weight-only https://ai-muninn.com/en/blog/dgx-spark-gemma4-12b-omni-nvfp4-weight-only Thu, 04 Jun 2026 00:00:00 GMT DGX Spark GB10 Gemma 4 NVFP4 FP8 quantization vLLM omni multimodal benchmark <![CDATA[[AI Agent] My Local Agent Flailed at Image Gen — It Was the Harness, Not the Weights]]> https://ai-muninn.com/en/blog/dgx-spark-agent-harness-not-weights https://ai-muninn.com/en/blog/dgx-spark-agent-harness-not-weights Tue, 02 Jun 2026 00:00:00 GMT AI Agent ACI harness ComfyUI DGX Spark Qwen3.6 tool design Hermes local LLM agent infrastructure <![CDATA[[Benchmark] NVFP4 shrinks a video model 33% on a DGX Spark — with zero speed gain]]> https://ai-muninn.com/en/blog/dgx-spark-sulphur-nvfp4-video https://ai-muninn.com/en/blog/dgx-spark-sulphur-nvfp4-video Mon, 01 Jun 2026 00:00:00 GMT NVFP4 Sulphur 2 LTX-2.3 DGX Spark GB10 video generation ComfyUI quantization diffusion benchmark <![CDATA[[Benchmark] NVFP4 W4A4 beats FP8 on a DGX Spark MoE: 67 vs 52 tok/s once CUDA graphs fire]]> https://ai-muninn.com/en/blog/dgx-spark-nvfp4-w4a4-moe-cudagraph https://ai-muninn.com/en/blog/dgx-spark-nvfp4-w4a4-moe-cudagraph Mon, 01 Jun 2026 00:00:00 GMT NVFP4 W4A4 FP8 DGX Spark GB10 SM121 vLLM MoE CUDA graph MTP benchmark <![CDATA[NVFP4 is 1.5× FP8 on a DGX Spark — but it's compression, not the FP4 cores]]> https://ai-muninn.com/en/blog/dgx-spark-nvfp4-compression-not-compute https://ai-muninn.com/en/blog/dgx-spark-nvfp4-compression-not-compute Sat, 30 May 2026 00:00:00 GMT NVFP4 FP8 DGX Spark GB10 SM121 vLLM benchmark quantization bandwidth <![CDATA[[LLM 101 #7] How to spot AI hallucinations — three red flags before you verify]]> https://ai-muninn.com/en/blog/llm-101-spot-ai-hallucination https://ai-muninn.com/en/blog/llm-101-spot-ai-hallucination Sat, 23 May 2026 00:00:00 GMT LLM hallucination beginner verification ChatGPT <![CDATA[Round 2 EAGLE-3 retrain didn't break the ceiling — a 60-hour null-result writeup]]> https://ai-muninn.com/en/blog/dgx-spark-eagle3-round2-null-result https://ai-muninn.com/en/blog/dgx-spark-eagle3-round2-null-result Thu, 21 May 2026 00:00:00 GMT Gemma 4 abliteration EAGLE-3 speculative decoding vLLM speculators DGX Spark GB10 FP8 huihui-ai fine-tune benchmark null result <![CDATA[[Claude Code] Rules I'd Skip, Hooks I Can't — I Wrote a Hook That Blocks My Own Blog Commits]]> https://ai-muninn.com/en/blog/claude-code-publish-gate-hook https://ai-muninn.com/en/blog/claude-code-publish-gate-hook Tue, 19 May 2026 00:00:00 GMT Claude Code hooks skills verification debt AI Workflow git commit publish gate self-modification agent self-improvement <![CDATA[EAGLE-3 fine-tune against an abliterated Gemma 4 body — Round 1 flattens the acceptance curve (plus a measurement lesson)]]> https://ai-muninn.com/en/blog/dgx-spark-eagle3-finetune-abliterated-round1 https://ai-muninn.com/en/blog/dgx-spark-eagle3-finetune-abliterated-round1 Sat, 16 May 2026 00:00:00 GMT Gemma 4 abliteration EAGLE-3 speculative decoding vLLM speculators DGX Spark GB10 FP8 huihui-ai fine-tune benchmark <![CDATA[30 lines of docker for +34% on DGX Spark: huihui Gemma 4 FP8 + vanilla MTP n=1 deployment recipe]]> https://ai-muninn.com/en/blog/dgx-spark-huihui-gemma4-mtp-n1-recipe https://ai-muninn.com/en/blog/dgx-spark-huihui-gemma4-mtp-n1-recipe Thu, 14 May 2026 00:00:00 GMT Gemma 4 abliteration MTP speculative decoding vLLM DGX Spark GB10 FP8 huihui-ai deployment recipe <![CDATA[Want MTP speedup on abliterated Gemma 4? Vanilla draft can't track the modified body]]> https://ai-muninn.com/en/blog/dgx-spark-huihui-gemma4-fp8-mtp-34pct https://ai-muninn.com/en/blog/dgx-spark-huihui-gemma4-fp8-mtp-34pct Sat, 09 May 2026 00:00:00 GMT Gemma 4 abliteration MTP speculative decoding vLLM DGX Spark GB10 FP8 huihui-ai benchmark <![CDATA[Liftoff: Gemma 4 hits 670 tok/s aggregate on DGX Spark (108 tok/s single-stream)]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-mtp-108-toks https://ai-muninn.com/en/blog/dgx-spark-gemma4-mtp-108-toks Wed, 06 May 2026 00:00:00 GMT Gemma 4 MTP speculative decoding vLLM DGX Spark GB10 SM121 FP8 NVFP4 benchmark Gemma 4 26B-A4B <![CDATA[How a zh-TW Linter Found 128 Mainland-China Drift in My Own Writing]]> https://ai-muninn.com/en/blog/zhtw-mcp-calque-blindspot-sweep https://ai-muninn.com/en/blog/zhtw-mcp-calque-blindspot-sweep Tue, 05 May 2026 00:00:00 GMT zh-TW AI Workflow linter skills calque localization zhtw-mcp sysprog21 writing pipeline Traditional Chinese LLM bias Claude Code <![CDATA[[Field Guide] Z-Image Turbo — does choosing a faster config hurt quality? LPIPS + CLIPScore answer]]> https://ai-muninn.com/en/blog/zimage-turbo-quality-lpips-clipscore https://ai-muninn.com/en/blog/zimage-turbo-quality-lpips-clipscore Mon, 04 May 2026 00:00:00 GMT Z-Image ComfyUI NVFP4 FP8 DGX Spark GB10 image gen benchmark quantization LPIPS CLIPScore quality Z-Image Turbo <![CDATA[[Field Guide] Z-Image Turbo — choosing the right config (1.37× faster, 44% less RAM)]]> https://ai-muninn.com/en/blog/dgx-spark-zimage-turbo-nvfp4-bench https://ai-muninn.com/en/blog/dgx-spark-zimage-turbo-nvfp4-bench Mon, 04 May 2026 00:00:00 GMT Z-Image ComfyUI NVFP4 FP8 DGX Spark GB10 SM121 image gen benchmark quantization Z-Image Turbo <![CDATA[[vLLM] Watching English Videos with DGX Spark: Nemotron Omni Multimodal on GB10]]> https://ai-muninn.com/en/blog/dgx-spark-nemotron-omni-multimodal-video https://ai-muninn.com/en/blog/dgx-spark-nemotron-omni-multimodal-video Fri, 01 May 2026 00:00:00 GMT Nemotron Omni multimodal vLLM DGX Spark GB10 video understanding Parakeet audio transcription Nemotron 3 Nano Omni Nemotron 3 Nano Omni 30B-A3B <![CDATA[[vLLM] Nemotron 3 Nano on DGX Spark: 74.75 tok/s NVFP4 — 11.5% Past the Public Baseline]]> https://ai-muninn.com/en/blog/dgx-spark-nemotron-3-nano-w4a16-74-toks https://ai-muninn.com/en/blog/dgx-spark-nemotron-3-nano-w4a16-74-toks Fri, 01 May 2026 00:00:00 GMT Nemotron 3 NVFP4 vLLM DGX Spark GB10 SM121 MoE W4A16 b12x benchmark Nemotron 3 Nano Nemotron 3 Nano 30B-A3B <![CDATA[Vercel Hobby hit 1M/1M Edge Requests. The bug was a Cache-Control header.]]> https://ai-muninn.com/en/blog/vercel-edge-requests-must-revalidate-trap https://ai-muninn.com/en/blog/vercel-edge-requests-must-revalidate-trap Thu, 30 Apr 2026 00:00:00 GMT Vercel Next.js Cache-Control Edge Network Performance Postmortem <![CDATA[[SWE-bench] Where Qwen 3.6 35B Loses on SWE-bench Lite: Anatomy of 155 Unresolved Tasks]]> https://ai-muninn.com/en/blog/swe-bench-qwen36-failure-modes https://ai-muninn.com/en/blog/swe-bench-qwen36-failure-modes Tue, 28 Apr 2026 00:00:00 GMT SWE-bench Qwen 3.6 Gemma 4 failure analysis open-source models scaffold DGX Spark wrong_logic Qwen 3.6 35B-A3B <![CDATA[[llm-compressor] Self-Quantizing a 35B Abliterated MoE to FP8 on DGX Spark: 4 OOMs, 3 Prefix Bugs, and Why the First Success Wasn't Actually FP8]]> https://ai-muninn.com/en/blog/dgx-spark-abliterated-fp8-uma-quantization https://ai-muninn.com/en/blog/dgx-spark-abliterated-fp8-uma-quantization Tue, 28 Apr 2026 00:00:00 GMT DGX Spark GB10 SM121 llm-compressor FP8 FP8_DYNAMIC abliteration Qwen 3.6 MoE UMA OOM MTP speculative-decoding quantization Qwen 3.6 35B-A3B <![CDATA[[Benchmark] Abliteration Costs 1.85pp on Traditional Chinese — and 7.7pp on Trust Law]]> https://ai-muninn.com/en/blog/tmmluplus-qwen-abliterated-cost https://ai-muninn.com/en/blog/tmmluplus-qwen-abliterated-cost Sun, 26 Apr 2026 00:00:00 GMT TMMLU+ abliteration Traditional Chinese Qwen 3.6 uncensored huihui-ai DGX Spark vLLM <![CDATA[[Benchmark] TMMLU+ Paired Eval: Qwen 3.6 35B Sweeps Gemma 4 26B 51-of-51 on Traditional Chinese]]> https://ai-muninn.com/en/blog/tmmluplus-qwen-vs-gemma-traditional-chinese https://ai-muninn.com/en/blog/tmmluplus-qwen-vs-gemma-traditional-chinese Sat, 25 Apr 2026 00:00:00 GMT TMMLU+ Traditional Chinese Qwen 3.6 Gemma 4 benchmark 繁體中文 DGX Spark vLLM lm-evaluation-harness <![CDATA[[Hands-On] Making NVFP4 17% Faster on GB10 with a Triton FP8 Bypass]]> https://ai-muninn.com/en/blog/dgx-spark-nvfp4-fp8-triton-patch https://ai-muninn.com/en/blog/dgx-spark-nvfp4-fp8-triton-patch Wed, 22 Apr 2026 00:00:00 GMT NVFP4 FP8 Triton DGX Spark GB10 SM121 vLLM Qwen 3.6 Qwen 3.6 35B-A3B kernel quantization tensor core <![CDATA[[Benchmark] NVFP4 Is a Trap on GB10: FP8 Wins by 32% (vLLM + SGLang Tested)]]> https://ai-muninn.com/en/blog/dgx-spark-nvfp4-trap-gb10-fp8-wins https://ai-muninn.com/en/blog/dgx-spark-nvfp4-trap-gb10-fp8-wins Tue, 21 Apr 2026 00:00:00 GMT NVFP4 FP8 DGX Spark GB10 SM121 vLLM SGLang Qwen 3.6 Qwen 3.6 35B-A3B benchmark quantization <![CDATA[[Benchmark] Same Scaffold, Three Models: 16% → 38% → 48% on SWE-bench Lite]]> https://ai-muninn.com/en/blog/swe-bench-scaffold-transfers-three-models https://ai-muninn.com/en/blog/swe-bench-scaffold-transfers-three-models Mon, 20 Apr 2026 00:00:00 GMT SWE-bench Gemma 4 Qwen 3.6 scaffold mini-swe-agent vLLM DGX Spark benchmark open-source Gemma 4 26B-A4B Qwen 3.6 35B-A3B <![CDATA[[Benchmark] SWE-bench Lite 38.67% with a 26B Local Model — 0.33% from Claude 3.5 Sonnet Scaffolds]]> https://ai-muninn.com/en/blog/swe-bench-lite-gemma4-26b-38-percent https://ai-muninn.com/en/blog/swe-bench-lite-gemma4-26b-38-percent Fri, 17 Apr 2026 00:00:00 GMT SWE-bench Gemma 4 mini-swe-agent vLLM DGX Spark benchmark open-source scaffold edit-tool Gemma 4 26B-A4B <![CDATA[[LLM 101 #6] Why Run AI on Your Own Computer? It's Not a Cheaper ChatGPT — It's a Different Tool]]> https://ai-muninn.com/en/blog/llm-101-why-run-ai-locally https://ai-muninn.com/en/blog/llm-101-why-run-ai-locally Fri, 17 Apr 2026 00:00:00 GMT LLM Local AI Ollama Beginner Privacy Cost <![CDATA[[Ask AI Right #7] What AI Does Poorly — Four Landmines to Know Before Using ChatGPT or Claude in 2026]]> https://ai-muninn.com/en/blog/ai-ask-right-what-ai-does-poorly https://ai-muninn.com/en/blog/ai-ask-right-what-ai-does-poorly Thu, 16 Apr 2026 00:00:00 GMT AI Hallucination ChatGPT Claude Privacy Beginner <![CDATA[[AI Agent] Gemma 4 26B Cleared a SWE-bench Lite Instance — After 28 Tries Across Two Days]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-swe-bench-scaffold-engineering https://ai-muninn.com/en/blog/dgx-spark-gemma4-swe-bench-scaffold-engineering Wed, 15 Apr 2026 00:00:00 GMT SWE-bench mini-swe-agent Gemma 4 vLLM agent scaffold GX10 Gemma 4 26B-A4B <![CDATA[[LLM Deep Dive] What Quantization Algorithms Actually Do: From Q4_K_M to TurboQuant]]> https://ai-muninn.com/en/blog/llm-deep-dive-quantization-algorithms https://ai-muninn.com/en/blog/llm-deep-dive-quantization-algorithms Wed, 15 Apr 2026 00:00:00 GMT LLM Quantization K-quant TurboQuant PolarQuant QJL Algorithms <![CDATA[[Ask AI Right #6] The Art of Follow-Up Questions — What to Do When the First Answer Is Too Shallow]]> https://ai-muninn.com/en/blog/ai-ask-right-follow-up-questions https://ai-muninn.com/en/blog/ai-ask-right-follow-up-questions Tue, 14 Apr 2026 00:00:00 GMT AI Conversation Follow-up Beginner Productivity <![CDATA[[LLM 101 #5] Context Window — How Much Can AI Read at Once?]]> https://ai-muninn.com/en/blog/llm-101-context-window https://ai-muninn.com/en/blog/llm-101-context-window Tue, 14 Apr 2026 00:00:00 GMT LLM Context Window Beginner Tokens AI Memory <![CDATA[[AI Agent] Gemma 4 Went from 40 Errors to a 9-Step Bug Fix — by Switching One Thing]]> https://ai-muninn.com/en/blog/swe-bench-local-models-framework-matters https://ai-muninn.com/en/blog/swe-bench-local-models-framework-matters Mon, 13 Apr 2026 00:00:00 GMT SWE-Bench Gemma 4 Qwen 3.5 OpenHands SWE-agent vLLM DGX Spark Tool Calling AI Agent Gemma 4 26B-A4B Qwen 3.5 35B <![CDATA[[Benchmark] Gemma 4 on DGX Spark — Which Model Should You Pick?]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-complete-guide https://ai-muninn.com/en/blog/dgx-spark-gemma4-complete-guide Mon, 13 Apr 2026 00:00:00 GMT Gemma 4 DGX Spark GB10 benchmark MoE NVFP4 vLLM Ollama DGX Spark worth it DGX Spark vs RTX 5090 best model DGX Spark 2026 <![CDATA[Claude Code Burning Through Tokens? 8 Fixes to Make Sessions Last 10x Longer]]> https://ai-muninn.com/en/blog/dev-workflow-token-burn-rate https://ai-muninn.com/en/blog/dev-workflow-token-burn-rate Mon, 13 Apr 2026 00:00:00 GMT Claude Code tokens context window beginner tips MCP CLAUDE.md knowledge graph musubi QMD AI cost save tokens <![CDATA[[Ask AI Right #5] Before You Build It, Ask: Does This Already Exist?]]> https://ai-muninn.com/en/blog/ai-ask-right-does-it-exist https://ai-muninn.com/en/blog/ai-ask-right-does-it-exist Mon, 13 Apr 2026 00:00:00 GMT AI Tools Research Beginner Productivity <![CDATA[[Claude Code] Build a Self-Auditing Skill That Keeps Your Config Lean]]> https://ai-muninn.com/en/blog/claude-code-slim-self-audit-skill https://ai-muninn.com/en/blog/claude-code-slim-self-audit-skill Mon, 13 Apr 2026 00:00:00 GMT Claude Code tokens context window skills CLAUDE.md MEMORY.md config optimization self-audit QMD AI Workflow <![CDATA[[DGX Spark] From Unboxing to Running: Complete Deployment Guide]]> https://ai-muninn.com/en/blog/dgx-spark-deployment-guide https://ai-muninn.com/en/blog/dgx-spark-deployment-guide Mon, 13 Apr 2026 00:00:00 GMT DGX Spark GB10 GX10 vLLM Ollama deployment Blackwell SM121 DGX Spark worth it DGX Spark setup 2026 DGX Spark vs RTX 5090 Gemma 4 Gemma 4 26B-A4B <![CDATA[[Ask AI Right #4] Why AI Feels Useless to You — Answer Machine vs Collaboration Tool]]> https://ai-muninn.com/en/blog/ai-ask-right-why-ai-feels-useless https://ai-muninn.com/en/blog/ai-ask-right-why-ai-feels-useless Sat, 11 Apr 2026 00:00:00 GMT AI ChatGPT Prompting Beginner Workflow Mindset <![CDATA[[LLM 101 #4] What Is Quantization? Q4, Q8, FP16 Explained]]> https://ai-muninn.com/en/blog/llm-101-what-is-quantization https://ai-muninn.com/en/blog/llm-101-what-is-quantization Fri, 10 Apr 2026 00:00:00 GMT LLM Quantization Ollama Beginner Q4_K_M GGUF <![CDATA[[Ask AI Right #3] You Don't Know What You Need — Let AI Find It]]> https://ai-muninn.com/en/blog/ai-ask-right-find-your-needs https://ai-muninn.com/en/blog/ai-ask-right-find-your-needs Fri, 10 Apr 2026 00:00:00 GMT AI Productivity Beginner Workflow <![CDATA[[LLM 101 #3] How to Choose an AI Model: Gemma vs Llama vs Qwen vs Mistral (2026)]]> https://ai-muninn.com/en/blog/llm-101-how-to-choose-a-model https://ai-muninn.com/en/blog/llm-101-how-to-choose-a-model Fri, 10 Apr 2026 00:00:00 GMT LLM Model Selection Ollama Beginner Gemma Llama Qwen <![CDATA[[Ask AI Right #2] You Opened AI — Now What Do You Say?]]> https://ai-muninn.com/en/blog/ai-ask-right-first-message https://ai-muninn.com/en/blog/ai-ask-right-first-message Thu, 09 Apr 2026 00:00:00 GMT AI ChatGPT Beginner Conversation <![CDATA[[Ask AI Right #1] Which AI Should You Use in 2026?]]> https://ai-muninn.com/en/blog/ai-ask-right-which-ai-to-use-2026 https://ai-muninn.com/en/blog/ai-ask-right-which-ai-to-use-2026 Thu, 09 Apr 2026 00:00:00 GMT AI ChatGPT Claude Gemini Beginner <![CDATA[[Benchmark] Rescuing Gemma 4 31B on a 32GB MacBook Pro: From 1.5 to 12.8 tok/s]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-31b-rescue-mbp-32gb https://ai-muninn.com/en/blog/dgx-spark-gemma4-31b-rescue-mbp-32gb Wed, 08 Apr 2026 00:00:00 GMT Gemma 4 31B M1 Max Ollama oMLX swap KV cache TurboQuant Apple Silicon memory management Gemma 4 31B <![CDATA[[Benchmark] 4 Machines, 4 Models, 1 Answer: Memory Decides Everything]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-4-machines-4-models-bandwidth https://ai-muninn.com/en/blog/dgx-spark-gemma4-4-machines-4-models-bandwidth Wed, 08 Apr 2026 00:00:00 GMT bandwidth.]]> Gemma 4 RTX 5090 DGX Spark GB10 M1 Max M4 Ollama benchmark memory bandwidth swap E2B E4B 26B 31B <![CDATA[[LLM 101 #2] Dense, MoE, PLE, SSM — Four AI Model Architectures Explained Simply]]> https://ai-muninn.com/en/blog/llm-101-dense-moe-ple-ssm-architectures https://ai-muninn.com/en/blog/llm-101-dense-moe-ple-ssm-architectures Wed, 08 Apr 2026 00:00:00 GMT Dense MoE PLE SSM Mamba LLM model architecture beginner explainer <![CDATA[[Benchmark] Gemma 4 E2B vs E4B: 81 tok/s vs 52 on Three Machines — Bandwidth Is Everything]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-e2b-vs-e4b-ollama-3-machines https://ai-muninn.com/en/blog/dgx-spark-gemma4-e2b-vs-e4b-ollama-3-machines Tue, 07 Apr 2026 00:00:00 GMT Gemma 4 E2B E4B Ollama benchmark DGX Spark GB10 M1 Max M4 Apple Silicon memory bandwidth Gemma 4 E2B Gemma 4 E4B <![CDATA[[Benchmark] From 19 to 50 tok/s: We Quantized Gemma 4 E4B to NVFP4 Before Anyone Else]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-e4b-nvfp4-50-toks https://ai-muninn.com/en/blog/dgx-spark-gemma4-e4b-nvfp4-50-toks Tue, 07 Apr 2026 00:00:00 GMT Gemma 4 E4B NVFP4 FP8 vLLM DGX Spark GB10 quantization llm-compressor PLE HuggingFace Gemma 4 E4B <![CDATA[[LLM 101 #1] Ollama vs vLLM: Two Ways to Run AI on Your Own Computer]]> https://ai-muninn.com/en/blog/llm-101-ollama-vs-vllm https://ai-muninn.com/en/blog/llm-101-ollama-vs-vllm Tue, 07 Apr 2026 00:00:00 GMT Ollama vLLM LLM local AI beginner explainer <![CDATA[[Benchmark] Gemma 4 31B Dense on DGX Spark: 7 tok/s and the Bandwidth Wall]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-31b-dense-7-toks https://ai-muninn.com/en/blog/dgx-spark-gemma4-31b-dense-7-toks Sun, 05 Apr 2026 00:00:00 GMT Gemma 4 NVFP4 vLLM DGX Spark GB10 SM121 dense benchmark bandwidth Gemma 4 31B Gemma 4 31B-IT <![CDATA[[Benchmark] vLLM vs Ollama on the Same Model: Why 30% Faster on GB10]]> https://ai-muninn.com/en/blog/dgx-spark-vllm-vs-ollama-same-model https://ai-muninn.com/en/blog/dgx-spark-vllm-vs-ollama-same-model Sun, 05 Apr 2026 00:00:00 GMT vLLM Ollama benchmark DGX Spark GB10 Gemma 4 NVFP4 inference Gemma 4 26B-A4B <![CDATA[Gemma 4 26B-A4B on DGX Spark: 52 tok/s with NVFP4, skip the 31B]]> https://ai-muninn.com/en/blog/dgx-spark-gemma4-26b-nvfp4-52-toks https://ai-muninn.com/en/blog/dgx-spark-gemma4-26b-nvfp4-52-toks Sun, 05 Apr 2026 00:00:00 GMT Gemma 4 NVFP4 vLLM DGX Spark GB10 SM121 MoE benchmark Gemma 4 26B-A4B <![CDATA[[DGX Spark] Overheating, 100W Power Cap, 30W Safety Mode — Complete Diagnostic Guide]]> https://ai-muninn.com/en/blog/dgx-spark-30w-power-safety-mode https://ai-muninn.com/en/blog/dgx-spark-30w-power-safety-mode Thu, 02 Apr 2026 00:00:00 GMT GX10 GB10 DGX Spark power delivery vLLM hardware overheating 100W Carmack Gemma 4 Gemma 4 26B-A4B <![CDATA[[Benchmark] TurboQuant on GX10: Is 3-bit KV Cache Compression Actually Lossless?]]> https://ai-muninn.com/en/blog/turboquant-kv-cache-benchmark-gx10 https://ai-muninn.com/en/blog/turboquant-kv-cache-benchmark-gx10 Mon, 30 Mar 2026 00:00:00 GMT TurboQuant KV Cache Quantization vLLM Benchmark Qwen3.5 GX10 SM121 <![CDATA[[AI Agent] openclaw + ChatGPT OAuth: Run GPT-5.4 Agents Without API Credits]]> https://ai-muninn.com/en/blog/openclaw-chatgpt-oauth-gpt54-no-api-key https://ai-muninn.com/en/blog/openclaw-chatgpt-oauth-gpt54-no-api-key Tue, 24 Mar 2026 00:00:00 GMT openclaw GPT-5.4 ChatGPT OAuth AI agent <![CDATA[[AI Agent] NemoClaw Without the Cloud: Swapping Nemotron for a Local Ollama Model]]> https://ai-muninn.com/en/blog/nemoclaw-local-inference-ollama https://ai-muninn.com/en/blog/nemoclaw-local-inference-ollama Tue, 24 Mar 2026 00:00:00 GMT NemoClaw OpenClaw OpenShell Ollama vLLM AI Agent NVIDIA GX10 Local Inference <![CDATA[[AI Agent] How to Install NemoClaw on DGX Spark (4 Undocumented Fixes)]]> https://ai-muninn.com/en/blog/nemoclaw-install-gx10-from-scratch https://ai-muninn.com/en/blog/nemoclaw-install-gx10-from-scratch Mon, 23 Mar 2026 00:00:00 GMT NemoClaw OpenClaw OpenShell AI Agent NVIDIA DGX Spark GX10 GB10 <![CDATA[[AI Agent] What Is NemoClaw? NVIDIA's AI Agent Framework for DGX Spark Explained]]> https://ai-muninn.com/en/blog/nemoclaw-what-it-is-why-it-exists https://ai-muninn.com/en/blog/nemoclaw-what-it-is-why-it-exists Mon, 23 Mar 2026 00:00:00 GMT NemoClaw OpenClaw OpenShell AI Agent NVIDIA DGX Spark GX10 <![CDATA[[AI Agent] openclaw Real-Time Streaming via Telegram Bot API 9.5 sendMessageDraft]]> https://ai-muninn.com/en/blog/openclaw-telegram-sendmessagedraft-streaming https://ai-muninn.com/en/blog/openclaw-telegram-sendmessagedraft-streaming Sat, 21 Mar 2026 00:00:00 GMT openclaw Telegram streaming Bot API undici GLM <![CDATA[[AI Agent] openclaw + 131K Context: When max_tokens Goes Negative]]> https://ai-muninn.com/en/blog/openclaw-context-budget-negative-maxtokens https://ai-muninn.com/en/blog/openclaw-context-budget-negative-maxtokens Sat, 21 Mar 2026 00:00:00 GMT openclaw context window vLLM gpt-oss configuration <![CDATA[[vLLM] FP8 KV Cache on GB10: Why Outputs Collapse into Repetition Loops]]> https://ai-muninn.com/en/blog/dgx-spark-fp8-kvcache-repetition https://ai-muninn.com/en/blog/dgx-spark-fp8-kvcache-repetition Sat, 21 Mar 2026 00:00:00 GMT vLLM FP8 KV cache GB10 DGX Spark quantization SM121 Qwen 3.5 Qwen 3.5 35B <![CDATA[[Claude Code] claude-agent-sdk vs subprocess: Why Intermediate Turns Disappear]]> https://ai-muninn.com/en/blog/claude-code-agent-sdk-orchestrator https://ai-muninn.com/en/blog/claude-code-agent-sdk-orchestrator Sat, 21 Mar 2026 00:00:00 GMT Claude Code claude-agent-sdk multi-agent orchestrator Python asyncio <![CDATA[[AI Agent] openclaw: Why the Bot Went Silent — Tailscale, IPv6, and a Node.js Happy Eyeballs Trap]]> https://ai-muninn.com/en/blog/openclaw-telegram-ipv6-tailscale-silent-bot https://ai-muninn.com/en/blog/openclaw-telegram-ipv6-tailscale-silent-bot Thu, 19 Mar 2026 00:00:00 GMT Node.js Tailscale IPv6 undici Happy Eyeballs Telegram Debugging Networking <![CDATA[[vLLM] Running a 120B Model on DGX Spark at 60 tok/s — Zero API Cost, Six Bugs]]> https://ai-muninn.com/en/blog/part2-gpt-oss-120b-serve-script https://ai-muninn.com/en/blog/part2-gpt-oss-120b-serve-script Thu, 19 Mar 2026 00:00:00 GMT DGX Spark SM121 vLLM gpt-oss MXFP4 Blackwell LLM Serving <![CDATA[[vLLM] Qwen3.5-122B Runs. But at 14 tok/s.]]> https://ai-muninn.com/en/blog/part2-qwen-122b-14-toks-gdn-kernel-gap https://ai-muninn.com/en/blog/part2-qwen-122b-14-toks-gdn-kernel-gap Thu, 19 Mar 2026 00:00:00 GMT DGX Spark SM121 Qwen3.5-122B vLLM NVFP4 Marlin GDN LLM Serving <![CDATA[[AI Agent] openclaw: When the Agent Calls for Help]]> https://ai-muninn.com/en/blog/openclaw-callhelp-spawning-cli-from-agent-loop https://ai-muninn.com/en/blog/openclaw-callhelp-spawning-cli-from-agent-loop Wed, 18 Mar 2026 00:00:00 GMT AI Agent openclaw Codex LLM Agent Tools Local AI <![CDATA[[vLLM] Why Your DGX Spark Only Says "!!!!!": Debugging NVFP4 on SM121]]> https://ai-muninn.com/en/blog/part1-why-your-dgx-spark-says-exclamation-marks https://ai-muninn.com/en/blog/part1-why-your-dgx-spark-says-exclamation-marks Tue, 17 Mar 2026 00:00:00 GMT DGX Spark SM121 vLLM NVFP4 MXFP4 Blackwell CUDA LLM Serving <![CDATA[[AI Agent] The Codex-Executor Pattern: Keeping Agent Sessions Small]]> https://ai-muninn.com/en/blog/openclaw-codex-executor-agent-architecture https://ai-muninn.com/en/blog/openclaw-codex-executor-agent-architecture Mon, 16 Mar 2026 00:00:00 GMT AI Agent Claude Code Codex Agent Architecture OpenClaw <![CDATA[[vLLM] Nemotron-3-Super-120B on a Single GB10: Full Day Debug Log]]> https://ai-muninn.com/en/blog/dgx-spark-nemotron-120b-vllm https://ai-muninn.com/en/blog/dgx-spark-nemotron-120b-vllm Fri, 13 Mar 2026 00:00:00 GMT DGX Spark GB10 SM121 Nemotron vLLM NVFP4 Blackwell LLM Serving Nemotron 3 Super Nemotron 3 Super 120B <![CDATA[[vLLM] Ollama's KEEP_ALIVE Is Silently Eating Your vLLM Headroom]]> https://ai-muninn.com/en/blog/openclaw-ollama-vllm-gpu-conflict https://ai-muninn.com/en/blog/openclaw-ollama-vllm-gpu-conflict Sat, 07 Mar 2026 00:00:00 GMT vLLM Ollama GPU Memory DGX Spark GB10 LLM Serving <![CDATA[[vLLM] Don't Add --enable-chunked-prefill to SSM Models]]> https://ai-muninn.com/en/blog/openclaw-chunked-prefill-ssm-trap https://ai-muninn.com/en/blog/openclaw-chunked-prefill-ssm-trap Fri, 06 Mar 2026 00:00:00 GMT vLLM SSM Qwen DGX Spark LLM Serving Performance <![CDATA[[vLLM] Qwen3.5-35B at 47 tok/s on DGX Spark: Ollama to vLLM Migration Guide]]> https://ai-muninn.com/en/blog/dgx-spark-vllm-qwen35-setup https://ai-muninn.com/en/blog/dgx-spark-vllm-qwen35-setup Thu, 05 Mar 2026 00:00:00 GMT DGX Spark GB10 vLLM Ollama Qwen 3.5 Docker Blackwell AI Agent Qwen 3.5 35B <![CDATA[[AI Agent] Zero API Cost: Running OpenClaw on DGX Spark + Mac Mini]]> https://ai-muninn.com/en/blog/openclaw-dgx-spark-local-ai-agent https://ai-muninn.com/en/blog/openclaw-dgx-spark-local-ai-agent Thu, 05 Mar 2026 00:00:00 GMT OpenClaw AI Agent DGX Spark Mac Mini Self-Hosted Ollama SearXNG <![CDATA[[Benchmark] Pure MoE vs SSM Hybrid: Context Decay and Why It Matters for Agents]]> https://ai-muninn.com/en/blog/openclaw-moe-ssm-context-decay https://ai-muninn.com/en/blog/openclaw-moe-ssm-context-decay Sun, 01 Mar 2026 00:00:00 GMT Benchmark SSM MoE DGX Spark GB10 LLM Serving AI Agents <![CDATA[[Dev Workflow] I Made Two AIs Argue. The Disagreements Are the Point.]]> https://ai-muninn.com/en/blog/claude-code-debate-system https://ai-muninn.com/en/blog/claude-code-debate-system Thu, 26 Feb 2026 00:00:00 GMT Dev Workflow Claude Code Gemini Codex Multi-AI Code Review <![CDATA[[Claude Code] Testing iOS Apps with Claude Code: 81% Context Reduction]]> https://ai-muninn.com/en/blog/claude-code-ios-testing-bpstracker https://ai-muninn.com/en/blog/claude-code-ios-testing-bpstracker Thu, 26 Feb 2026 00:00:00 GMT Claude Code iOS Swift Testing Fastlane BPS Tracker <![CDATA[[AI Agent] OpenClaw Config Hot-Reload: No Restart Needed]]> https://ai-muninn.com/en/blog/openclaw-config-hot-reload https://ai-muninn.com/en/blog/openclaw-config-hot-reload Wed, 25 Feb 2026 00:00:00 GMT AI Agent OpenClaw Configuration Developer Workflow <![CDATA[[Claude Code] I Wrote MANDATORY. The AI Ignored It.]]> https://ai-muninn.com/en/blog/claude-code-mandatory-instructions https://ai-muninn.com/en/blog/claude-code-mandatory-instructions Thu, 19 Feb 2026 00:00:00 GMT Claude Code AI Agents Prompt Engineering Systems Design Developer Workflow <![CDATA[[Benchmark] 8 Models on DGX Spark: Finding the Best Stack for AI Agents]]> https://ai-muninn.com/en/blog/dgx-spark-ollama-benchmark-8-models https://ai-muninn.com/en/blog/dgx-spark-ollama-benchmark-8-models Thu, 19 Feb 2026 00:00:00 GMT DGX Spark GB10 Ollama Benchmark LLM AI Agent Blackwell