#fastllm — Blog — ai-muninn

~ / blog / tag / fastllm

❯ grep -r "#fastllm" ~/blog

3 matches

datereadtitle
2026-09-2817m
NVFP4 Without FP4 Hardware: Qwen3.8-27B on Two RTX 2080 Tis at 151.7 tok/s
#fastllm #nvfp4 #quantization #2080-ti
2026-09-2821m
Dual RTX 2080 Ti FastLLM: 16% Faster Decoding and No More Head-of-Line Blocking
#fastllm #dflash2 #speculative-decoding #2080-ti
2026-09-2124m
Two Modded RTX 2080 Tis Hit 153.8 tok/s on Qwen3.8-27B With FastLLM + DFlash2
#fastllm #dflash2 #speculative-decoding #2080-ti

← back to all posts