This just a quantized version of 3.8 next flash on strata that’s branded?

I think the major difference is they have a set of profile data they use to manage the placement of expert weights.

"Hot" commonly used experts are kept on the GPU, and "cold" less used experts are bumped to system ram and calculated on the CPU. So it can run larger than vram sized models without completely crippling performance.

I'm not exactly sure what the changes they made to the architecture are for, perhaps they're aimed at extending the difference between the "hot" and "cold" expert usage?

▲

rurban a day ago | parent | prev | next [-]

And HIP support (amd) broken.

▲

selcuka a day ago | parent | prev | next [-]

I'm not saying it's not, but if this is the case, how do we think it beats 3.8FN in benchmarks?

▲

Aurornis a day ago | parent [-]

> I'm not saying it's not,

Their GitHub repo and HuggingFace pages directly state that it's based on Qwen3.8 Flash Next. Their inference engine is called edge0-strata because it's a strata fork.

They fine tuned it and tweaked the architecture.

The real question is if the model performs better on general purpose tasks, or if it was just fine tuned to increase the benchmark scores.

	▲	selcuka a day ago \| parent [-]
		Fair enough. I was just responding to the "just a quantized version of 3.8 next flash" claim. Benchmaxxing via fine-tuning is a very plausible possibility.

▲

cvadict a day ago | parent | prev | next [-]

100% my exact impression of this project as well

▲

baxtr 16 hours ago | parent | prev [-]

Similar to a Linux distribution then?