#ds4 — Blog — ai-muninn

~ / blog / tag / ds4

❯ grep -r "#ds4" ~/blog

11 matches

datereadtitle
2026-07-2515m
[DeepSeek-V4-Flash] The Engine Upgrade That OOM'd My DGX Spark — and Why I Rolled It Back
#deepseek-v4-flash #dgx-spark #ds4 #oom
2026-07-2112m
[DeepSeek-V4-Flash] Swapping the ds4 Engine for a Free Half-Generation Speedup on One DGX Spark
#deepseek-v4-flash #dgx-spark #ds4 #speculative-decoding
2026-07-0912m
[Local LLM] FlashMemory can't improve DeepSeek-V4-Flash's own lightning indexer — I retrained it on my exact Q2 and it still lost
#dgx-spark #gb10 #deepseek-v4-flash #kv-cache
2026-07-0712m
[Local LLM] Why a 284B fits a 128GB GB10 at long context: DeepSeek-V4-Flash attacks the KV cache, not the parameter count
#dgx-spark #gb10 #deepseek-v4-flash #kv-cache
2026-07-0610m
[Local LLM] Depth-1 MTP on V4-Flash: +9% on agent turns, −4% on prose — route speculative decode by workload
#dgx-spark #gb10 #deepseek-v4-flash #speculative-decoding
2026-07-0512m
[Local LLM] My 284B agent quietly stopped reusing its KV cache — the ds4 evict storm that re-paid prefill every turn
#dgx-spark #gb10 #deepseek-v4-flash #kv-cache
2026-06-2110m
Directional Steering on an Abliterated DeepSeek-V4 (DGX Spark): the same scalpel as abliteration, and why the second cut fights back
#deepseek-v4 #directional-steering #activation-steering #abliteration
2026-06-199m
[Agent 101 #9] Swap your assistant's brain for one on your own machine: from cloud ChatGPT to a local model
#ai-assistant #ai-agent #hermes #local-model
2026-06-127m
[Local LLM] Weights win: a 284B crushed to 2-bit still beats the small model that fits
#dgx-spark #gb10 #deepseek-v4-flash #quantization
2026-06-1214m
[Local LLM] Running a 15 tok/s 284B as your daily agent brain — the settings that make it bearable
#dgx-spark #gb10 #deepseek-v4-flash #kv-cache
2026-06-1210m
[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
#dgx-spark #gb10 #deepseek-v4-flash #ds4

← back to all posts