The Autodidacts

Exploring the universe from the inside out

Articles Tagged:

Llama.cpp

Subscribe to this tag’s RSS feed to get new Llama.cpp posts as they’re written.

A 1 post collection

Llama.cpp's llama-server web UI in action, running Qwen 3.6 35B A3B

How to fit Qwen 3.6 35B A3B into 16GB of VRAM, & run it with Llama.cpp on an RTX 3080

The belly hangs over the belt, but it fits … »