Edge0-145B: Frontier AI Capabilities on Your Own Computer (edge0.ai)
100 points by sroussey 5 hours ago
mikeshi42 2 hours ago
> Sharing matrices substantially reduces the weights that must be stored and moved while keeping the expert count unchanged. Each group of 64 experts shares two large matrices, while each expert retains a small set of parameters that captures its differences.
145B parameters with only peak 29GB memory usage - really impressive, truly something you can actually run on a decent spec MBP
SwellJoe 3 hours ago
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.
jazzyjackson an hour ago
Do they say how they interact with Blender? Launched within a python interpreter everything in Blender is accessible as a method call. I hope they didn’t do anything more complex than that.
mortalapeman 3 hours ago
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 2 hours ago
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.
anon373839 2 hours ago
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.
K0balt 2 hours ago
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.
nightdeployboy 5 minutes ago
Is the era of one seat per person AI coming?
PaulKeeble 2 hours ago
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.
coder543 an hour ago
They literally talked about MacBooks in the blog post, and they did release more than just NVFP4: https://huggingface.co/Edge0/Edge0-145B-q3k
It is strange that they also benchmarked an M2 Ultra, but they are specifically not releasing a Mac runtime today. Maybe that is still under development.
rybosome 3 hours ago
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!
fesoliveira 3 hours ago
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!
paulhart 2 hours ago
Are there any iOS apps that support the Edge0-35B model? I'm curious to try that out on-device.
Zetaphor 3 hours ago
This is not open source, this is open weights
hedora 2 hours ago
It is not open weight either. The license is too restrictive to meet the standard definition of that team.
quicklywilliam 39 minutes ago
This smells off.
suthakamal 2 hours ago
Why so little information about the company on the corporate website?
1612elphi 2 hours ago
I'm really glad they provided us with the graph of "Model Parameters over time", fucking lmao
devmor 2 hours ago
> Edge0-145B requires a compatible laptop with...
Damn, guess I can't run this on my desktop. /s
dyyd3333 3 hours ago
Ok buddy