Hacker News new | past | comments | ask | show | jobs | submit
mortalapeman | on: Edge0-145B: Frontier AI Capabilities on Your Own Computer
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 | 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 | root | 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.

loading story #50478093
Aurornis | parent | 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 | parent
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.