I have similar hardware - what specific version of the 3.8 Next model are you running and how many tokens/s are you seeing? 3.6 35B A3B gets about 68t/s for me so I've been sticking with that model for the mean time.

▲

throwa356262 3 hours ago | parent [-]

The thing with 3.8 next is that it uses a variant of ngrams. Part of the network is replaced by a lookup table you can store on a fast ssd.

In practice, you will be able to run models a bit bigger than 35B.

https://unsloth.ai/docs/models/qwen3.8-next

	▲	cyanydeez 2 hours ago \| parent [-]
		https://github.com/peonist-ai/halogen-server is beating the pants off of anything I've tried. 38GB of vram resident. more tk/s, more prefill.