alt Hacker NewsQwen3.8 27B seems like it was clearly supposed to be a high-end consumer open-weights model, but the t/s is so low for me on my old M1 Max 64GB that I hope others are getting use out of it.
Unfortunately, the calculus has changed and it seems cheaper to me to just use MiMo V2.5 for pennies or DeepSeek V4 Flash instead of using Qwen anymore unless I need a local model specifically for doing reverse engineering work that gets otherwise rejected.
Replies
Have you tried https://huggingface.co/prism-ml/Bonsai-27B-mlx-1bit ? PrismML is the only people i am aware of doing 1bit that is decent.
I leave it running at night. No danger of burning my token subscriptions and it has hours and hours to run slowly with a manager like: github.com/kunchenguid/gnhf
I treat it like image gen. Send a prompt then come back in 40 minutes.
> Qwen3.8 27B seems like it was clearly supposed to be a high-end consumer open-weights model, but the t/s is so low for me on my old M1 Max 64GB that I hope others are getting use out of it.
Have you tried it with MTPLX? I get around 30 tok/s with it, also on an M1 Max with 64GB.