Rendered at 15:58:21 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
mike_hearn 6 minutes ago [-]
That's very impressive. What's the best way to run these kernels natively on a Mac? I saw that there's a way to plug Claude into Apple's Foundation Models framework, and there's a CLI tool that can access models via that framework. It might be useful to have something so fast and good available via a small CLI tool for various purposes, especially when connected with a small suite of tools I have for things like file editing, showing, simple agentic purposes etc.
thomspoon 2 minutes ago [-]
Either ollama or omlx, both are pretty dang performant. Omlx lets you run Claude code locally though as long as you bootstrap it with the right model
nmfisher 7 minutes ago [-]
It's not immediately clear, but this seems to be 250 tok/s on an M4 Max.
For comparison, the current agent swarm challenge on HF is at 508 tok/s on a A10G GPU:
More of a meta comment, but I really wish anthropic would say something about their plans for Fable. We're all just kind of left here floating and aimless, with no idea of what to expect
rst 8 minutes ago [-]
They're kind of at the mercy of the US government on this, and the government seems to have them in the position you describe.
jauntywundrkind 10 minutes ago [-]
The US Government has demanded a solution to the Halting Problem squared and by George (Washington) these tinpot facsists are going to get what they demand.
Hard to imagine where things go from here. GLM-5.3 will be released some day, with Fable class capabilities, and the (MAGA) US government will still be faffing around in their alt-reality cinematic bullshitiverse.
For comparison, the current agent swarm challenge on HF is at 508 tok/s on a A10G GPU:
https://huggingface.co/spaces/gemma-challenge/gemma-dashboar...
Hard to imagine where things go from here. GLM-5.3 will be released some day, with Fable class capabilities, and the (MAGA) US government will still be faffing around in their alt-reality cinematic bullshitiverse.