I've been using the 35B-A3B today for some web scraping work, and it has been on par with Qwen3.8 27B at a much higher speed and at a higher quant (q4 vs q8). I'm impressed.

▲

jakswa 4 hours ago | parent | next [-]

I had to go down to UD-Q3_K_XL for Qwen 3.8 27B to get it to fit in VRAM and be usable, but I worry I'm gutting its intelligence somewhat. I too am interested in faster + more-usable alternative that can exchange blows with the Q3-dumbed 27B.

▲

jadbox 4 hours ago | parent | prev [-]

I need someone to run actual benchmarks between the two.

	▲	swatcoder 4 hours ago \| parent \| next [-]
		Benchmarks are the BMI of model evaluation. They may have utility in trying to look at the whole landscape of models, but are very misleading when it comes to making 1:1 comparisons or in developing confidence at to how a given model will deliver on your workflow.
	▲	gertlabs 3 hours ago \| parent \| prev \| next [-]
		These models have gotten a fair amount of attention -- we're hoping it's enough to get them added to some reliable inference providers and OpenRouter, at which point we'll run them on our full benchmark suite.
	▲	NitpickLawyer 3 hours ago \| parent \| prev [-]
		Only relevant benchmarks are those you make yourself, targeted specifically for your workflows. Anything else is just number go up on a pretty graph, and every model out there is probably benchmaxxed to hell on the public ones anyway. Keep yours private.