3 posts
Posts tagged Local LLM
-
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.
-
How much VRAM an LLM really uses
The back-of-the-envelope math — parameters times bits — is off by several gigabytes, because it ignores the KV cache. Here is the full calculation, with the formula, the numbers and how to verify it on your own GPU.
-
I measured whether a spec file makes the model more accurate. It doesn't.
In July I argued that structured spec changes the outcome. I measured in October: 360 generations, 3 local models, 3 ways of asking for the same thing. What pays off is the written information, not the file format.