News for hackers. Stuff that matters.

A comment on Edge0-145B: Frontier AI Capabilities on Your Own Computer. Parent comment

Re:Edge0-145B: Frontier AI Capabilities on Your Own Computer by kimixa on Thursday November 12, 2026 @08:25PM (#50476908)
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

[ Parent | on HN ]
Re:Edge0-145B: Frontier AI Capabilities on Your Own Computer by anon373839 on Thursday November 12, 2026 @08:53PM (#50477085)
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.
[ Parent | on HN ]
Re:Edge0-145B: Frontier AI Capabilities on Your Own Computer by sroussey on Thursday November 12, 2026 @10:58PM (#50478093)
If you look closely there is also a 25B, tho you question still stands.
[ Parent | on HN ]
Re:Edge0-145B: Frontier AI Capabilities on Your Own Computer by sroussey on Thursday November 12, 2026 @11:06PM (#50478155)
Their GitHub also references that:

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

[ Parent | on HN ]