跳到正文
Hacker News:AI 熱帖·· 9 天前AI 評分47

Edge0-145B:在個人電腦上實現前沿 AI 能力

Edge0-145B: Frontier AI Capabilities on Your Own Computer

AI 導讀

Edge0-145B 主打在個人電腦上提供前沿 AI 能力,討論者提及其 Blender 範例及 TerminalBench 表現。留言指出,模型以 NVFP4 發佈,可能只支援 Nvidia Blackwell;亦有留言提醒它屬於開放權重,而非開源。

正文

Image 1Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Edge0-145B: Frontier AI Capabilities on Your Own Computer (edge0.ai) 33 points by sroussey2 hours ago | hide | past | favorite | 9 comments help Image 2PaulKeeble7 minutes ago | next[–] Thy have shipped this as NVFP4 so its Nvidia blackwell only, presumably their inference engine doesn't support anything outside CUDA 13 specified either. Will be interesting to see if this gains some other quants and other inference engines pick it up and we get some standard GGUF files, its a bit of weird release at the moment rather than GGUF file downloads the variants link on HF is leading to a directory of stuff which contains the model spread across a variety of files. reply Image 3SwellJoe36 minutes ago | prev | next[–] I'm really impressed with the Blender examples. It's amazing how far "tool use" has come, when it now means using a tool as complicated as Blender to perform work that would take a human days to complete. I'm a little skeptical the actual models are workable, in the sense that a human could come in after and manually refine and apply better textures, etc. Historically, agent-made designs are messy as hell, and by the time you clean them up, you haven't saved any time. But, that's begun to get better; the best models are now very good at making clean shape-based SVGs, for example, that are no messier than what a human would make in Inkscape or Illustrator. But, I'll definitely give it a try. reply Image 4paulhart9 minutes ago | prev | next[–] Are there any iOS apps that support the Edge0-35B model? I'm curious to try that out on-device. reply Image 5rybosome28 minutes ago | prev | next[–] TerminalBench scores often correspond to real world performance for coding agents that rely heavily on bash. This score is roughly on par with 5.6 Terra max, which in my direct experience is perfectly capable of driving a cloud agent harness that can do pretty complex knowledge work. Definitely worth an evaluation! reply Image 6mortalapeman56 minutes ago | prev | next[–] 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. reply Image 7kimixa3 minutes 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 reply Image 8fesoliveira49 minutes ago | prev | next[–] Interesting, if 3rd party testing and benchmarking hold the published values this is very exciting. I am a bit skeptical given the model size, but I hope it turns out to be true! reply Image 9Zetaphor50 minutes ago | prev | next[–] This is not open source, this is open weights reply Image 10dyyd33331 hour ago | prev[–] Ok buddy reply Image 11 Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:

來源:Hacker News:AI 熱帖 · news.ycombinator.com