Really happy for those with 128GB+ RAM. Sitting here with my Apple M1 Max with 64GB though. Was looking forward to a Qwen3.8-35B-A3B like many others.

▲ dofm 4 hours ago | parent [-]

Have you tested Muse Glimmer in low reasoning strength?

Token generation is slow (and prefill is) but you will likely find it solves actual problems faster than Qwen 3.6 35B-A3B.

▲ bellowsgulch 4 hours ago | parent [-]

I’ll give it a try! Thanks for the heads up!

	▲	dofm 3 hours ago \| parent [-]
		I’m using the Unsloth 4-bit quant. To change the reasoning strength you just put text in the system prompt. From memory it is: `Reasoning strength: low`