1 post
Posts tagged Qwen
-
Qwen3.6 27B: How Much VRAM It Really Needs
A 27B model that uses half the KV cache of a Llama 3 8B. The hybrid architecture breaks the usual calculation — and decides, for less than 1 GB, which cards are left out.
1 post
A 27B model that uses half the KV cache of a Llama 3 8B. The hybrid architecture breaks the usual calculation — and decides, for less than 1 GB, which cards are left out.