Is this a derived from flash next? That's the impression I get from reading over everything. Using Strata + Qwen 3.8 Flash Next now and I am beyond impressed. It's basically as capable as 5.6 Luna in my hands so far. If this is an upgrade I can't wait to try it out.

▲

kimixa a day ago | parent | next [-]

I assume so - Qwen/Qwen3.8-Flash-Next is marked as the "Base Model" on the huggingface page and states it may be subject to "Qwen's separate authorization or attribution requirements"

And I assume the metrics comparing qwen are using a quantized version - from the blog they compare memory use against qwen's "standard 4-bit deployment". Which might explain the improved performance over that base model they show - it might lose less from quantization.

https://huggingface.co/Edge0/Edge0-145B-NVFP4

▲

anon373839 a day ago | parent | next [-]

It's interesting. It does seem to be based on QFN, but they've modified the architecture. 10B active versus QFN's 6B, plus also QFN is 180B parameters, not 145B. But it has the same 51B n-gram table.

Also, why ship both a 145B and a 120B size? That's basically the same size class.

	▲	sroussey a day ago \| parent [-]
		If you look closely there is also a 35B, tho your question still stands. There is also a reference to a 8B https://github.com/Edge0-AI/Edge0/tree/main/docs/models

▲

sroussey a day ago | parent | prev [-]

Their GitHub also references that:

https://github.com/Edge0-AI/Edge0/blob/main/licenses/edge0-m...

▲

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

> Using Strata + Qwen 3.8 Flash Next now and I am beyond impressed.

The inference engine they use is called edge0-strata because it's a strata fork.

This project looks like someone fine-tuned Qwen3.8 Flash Next, made some tweaks to the model, forked strata to run it, and then put a lot of marketing and branding on top of it

▲

K0balt a day ago | parent | prev [-]

3.8F/N is amazing. Truly useful, runnable local AI on machines that are not ridiculously expensive. (I’m running it on 2x 3090 and 128gb of ram, on the quantum roughly equivalent to 5-K-M. fast, but you can run it on much less

This looks like it would actually work on my 64mb M1 MBP. That would be fantastic.

▲

jckahn 15 hours ago | parent [-]

We have different definitions of "ridiculously expensive." To me, more than $3k is ridiculously expensive. What you described sounds a lot more expensive than that.

	▲	Tade0 11 hours ago \| parent \| next [-]
		If you're only interested in coding tasks, this version of QFN will fit in 64GB RAM: https://huggingface.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RC...
	▲	K0balt 12 hours ago \| parent \| prev \| next [-]
		When GPT4 ? 3.5? was all the rage, I started buying up AI gear because I saw memory starting to rise, so I bought 4x 3090s and 256gb of RAM, a couple mobos and some ryzen chips. I’m glad I did. It’s ridiculous that I could buy a decent used car for the price of this stuff now lol.
	▲	lowbloodsugar 11 hours ago \| parent \| prev [-]
		As a software professional, spending $8k on an RTX 6000 Blackwell was a reasonable investment in tools. I've learned so much, and now I have "free" Qwen3.8 Flash Next at NVFP4. I'm still using my M1 Macbook Max which was $5k. I don't think that's unreasonable money for a professional. Would I pay the current RTX 6000 price of $16k for the knowledge I've gained? I think I would. Luckily I got in early. Hobbyist, sure, too expensive for most? OTOH as a kid, my parents sweated to accumulate $5k worth of computer (and 5.25" drives!) in today's dollars, so that investment paid off.