~/ai-muninn
blog
github
中
~ / blog
/
tag / moe
❯
grep -r "#moe" ~/blog
6 matches
date
read
title
2026-05-01
13m
[vLLM] Nemotron 3 Nano on DGX Spark: 74.75 tok/s NVFP4 — 11.5% Past the Public Baseline
#nemotron-3
#nvfp4
#vllm
#dgx-spark
2026-04-28
13m
[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
#dgx-spark
#gb10
#sm121
#llm-compressor
2026-04-13
6m
[Benchmark] Gemma 4 Complete Guide on DGX Spark — Which Model Should You Pick?
#gemma-4
#dgx-spark
#gb10
#benchmark
2026-04-08
9m
[LLM 101] Dense, MoE, PLE, SSM — Four AI Model Architectures Explained Simply
#dense
#moe
#ple
#ssm
2026-04-05
8m
Gemma 4 26B in 16 GB at 52 tok/s — DGX Spark NVFP4
#gemma-4
#nvfp4
#vllm
#dgx-spark
2026-03-01
8m
[Benchmark] Pure MoE vs SSM Hybrid: Context Decay and Why It Matters for Agents
#benchmark
#ssm
#moe
#dgx-spark
← back to all posts