The Llama.cpp Fork That Enables Qwen 3.8 27B Large Contexts for 16GB VRAM GPU (github.com) 4 points by dazhbog 1mo ago ↗ HN
[–] dazhbog 1mo ago ↗ A video I found covering the improvementshttps://www.youtube.com/watch?v=n_ggLjIgRcM
[–] akshay_akula 1mo ago ↗ Will this perform better than lmstudio-community/Qwen3.8-27B-MLX-4bit on my m5 max 48gb memory mac?
3 comments
[ 5.8 ms ] story [ 20.1 ms ] threadhttps://www.youtube.com/watch?v=n_ggLjIgRcM