The Llama.cpp Fork That Enables Qwen 3.8 27B Large Contexts for 16GB VRAM GPU

5 points by dazhbog a month ago · 3 comments

Reader

2 threads

dazhbogOP a month ago

A video I found covering the improvements

akshay_akula a month ago

Will this perform better than lmstudio-community/Qwen3.8-27B-MLX-4bit on my m5 max 48gb memory mac?

Settings