#gemma-4 — Blog — ai-muninn

~ / blog / tag / gemma-4

❯ grep -r "#gemma-4" ~/blog

28 matches

datereadtitle
2026-07-078m
DGX Spark in 2026: What Still Works, What Broke, and What I'd Run Today
#dgx-spark #gb10 #gemma-4 #vllm
2026-06-1414m
[Just for Fun] A blog RAG support bot on a GTX 970: no torch, no vector DB, no LangChain
#gemma-4 #gtx-970 #rag #llama.cpp
2026-06-1410m
[Just for Fun] On a GTX 970, Flash Attention nearly doubles long-context decode (24.3 → 42.5 tok/s)
#gemma-4 #gtx-970 #flash-attention #kv-cache
2026-06-0910m
[Just for Fun] A GTX 970 as an offline voice assistant: Gemma 4 E2B + Piper TTS (2.8s end-to-end)
#gemma-4 #gtx-970 #multimodal #piper-tts
2026-06-0910m
[Just for Fun] Gemma 4 E2B on a GTX 970: the biggest quant runs fastest (47.6 tok/s)
#gemma-4 #quantization #gtx-970 #llama.cpp
2026-06-059m
[Benchmark] NVFP4 Weight-Only Quantization Taxes Chinese ~2x Harder Than English (gemma-4-12B)
#dgx-spark #gb10 #gemma-4 #nvfp4
2026-06-046m
[Benchmark] Gemma 4 12B Omni on DGX Spark: Weight-Only NVFP4 Beats W4A4 (and Keeps Multimodal)
#dgx-spark #gb10 #gemma-4 #nvfp4
2026-05-2110m
Round 2 EAGLE-3 retrain didn't break the ceiling — a 60-hour null-result writeup
#gemma-4 #abliteration #eagle-3 #speculative-decoding
2026-05-1614m
EAGLE-3 fine-tune against an abliterated Gemma 4 body — Round 1 flattens the acceptance curve (plus a measurement lesson)
#gemma-4 #abliteration #eagle-3 #speculative-decoding
2026-05-146m
30 lines of docker for +34% on DGX Spark: huihui Gemma 4 FP8 + vanilla MTP n=1 deployment recipe
#gemma-4 #abliteration #mtp #speculative-decoding
2026-05-0914m
Want MTP speedup on abliterated Gemma 4? Vanilla draft can't track the modified body
#gemma-4 #abliteration #mtp #speculative-decoding
2026-05-0615m
Liftoff: Gemma 4 hits 670 tok/s aggregate on DGX Spark (108 tok/s single-stream)
#gemma-4 #mtp #speculative-decoding #vllm
2026-04-289m
[SWE-bench] Where Qwen 3.6 35B Loses on SWE-bench Lite: Anatomy of 155 Unresolved Tasks
#swe-bench #qwen-3.6 #gemma-4 #failure-analysis
2026-04-257m
[Benchmark] TMMLU+ Paired Eval: Qwen 3.6 35B Sweeps Gemma 4 26B 51-of-51 on Traditional Chinese
#tmmlu+#traditional-chinese #qwen-3.6 #gemma-4
2026-04-207m
[Benchmark] Same Scaffold, Three Models: 16% → 38% → 48% on SWE-bench Lite
#swe-bench #gemma-4 #qwen-3.6 #scaffold
2026-04-1712m
[Benchmark] SWE-bench Lite 38.67% with a 26B Local Model — 0.33% from Claude 3.5 Sonnet Scaffolds
#swe-bench #gemma-4 #mini-swe-agent #vllm
2026-04-158m
[AI Agent] Gemma 4 26B Cleared a SWE-bench Lite Instance — After 28 Tries Across Two Days
#swe-bench #mini-swe-agent #gemma-4 #vllm
2026-04-137m
[AI Agent] Gemma 4 Went from 40 Errors to a 9-Step Bug Fix — by Switching One Thing
#swe-bench #gemma-4 #qwen-3.5 #openhands
2026-04-136m
[Benchmark] Gemma 4 on DGX Spark — Which Model Should You Pick?
#gemma-4 #dgx-spark #gb10 #benchmark
2026-04-138m
[DGX Spark] From Unboxing to Running: Complete Deployment Guide
#dgx-spark #gb10 #gx10 #vllm
2026-04-088m
[Benchmark] Rescuing Gemma 4 31B on a 32GB MacBook Pro: From 1.5 to 12.8 tok/s
#gemma-4 #31b #m1-max #ollama
2026-04-089m
[Benchmark] 4 Machines, 4 Models, 1 Answer: Memory Decides Everything
#gemma-4 #rtx-5090 #dgx-spark #gb10
2026-04-078m
[Benchmark] Gemma 4 E2B vs E4B: 81 tok/s vs 52 on Three Machines — Bandwidth Is Everything
#gemma-4 #e2b #e4b #ollama
2026-04-079m
[Benchmark] From 19 to 50 tok/s: We Quantized Gemma 4 E4B to NVFP4 Before Anyone Else
#gemma-4 #e4b #nvfp4 #fp8
2026-04-056m
[Benchmark] Gemma 4 31B Dense on DGX Spark: 7 tok/s and the Bandwidth Wall
#gemma-4 #nvfp4 #vllm #dgx-spark
2026-04-058m
[Benchmark] vLLM vs Ollama on the Same Model: Why 30% Faster on GB10
#vllm #ollama #benchmark #dgx-spark
2026-04-059m
Gemma 4 26B-A4B on DGX Spark: 52 tok/s with NVFP4, skip the 31B
#gemma-4 #nvfp4 #vllm #dgx-spark
2026-04-026m
[DGX Spark] Overheating, 100W Power Cap, 30W Safety Mode — Complete Diagnostic Guide
#gx10 #gb10 #dgx-spark #power-delivery

← back to all posts