devtool
Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE
A niche, hard-to-setup solution for running a 35B model on M1, only for enthusiasts.
4.1Overall
Utility5
Onboarding3
Craft3
Niche fit6
Longevity3
Five dimensions scored independently; overall is a weighted average. Scores are only comparable within this same rubric.
Good for
Developers or researchers who want to experiment with a 35B model on Apple Silicon locally
Not for
Teams or users needing a stable, production‑ready solution
Project description
github.com
Alternatives
llama.cpptext-generation-webuiggml