~/ai-muninn
search
⌘K
blog
model anatomy
github
中
~ / blog
/
tag / q6_k
❯
grep -r "#q6_k" ~/blog
1 match
date
read
title
2026-11-11
9m
[Benchmark] FP16 vs Q8 on RTX 5090: Qwen2.5-7B Generates at 188.75 tok/s
#fp16-vs-q8
#q8_0
#q6_k
#q4_k_m
← back to all posts