Comment by jedbrooke

the bonsai 27B 1bit quant version of Qwen3.6 27B is even more nuts, model fits in 4GB, and with 100k of content model+kv cache fits in 8GB. I’ve been running it locally on my mac mini 16GB. it gets around 4-6 tok/s, so not quite real-time ready, but good enough to let it run on task async for 20 min and come back. The 1bit model struggles a bit with multi-turn conversations though (e.g. when switching from plan to act mode it will still keep trying to make a plan) but that’s easy enough to reformat prompts into multiple one shot sessions of smaller work.