Fable 5 pushed Gemma 4 to 255 tok/s on WebGPU

Discussion (6 Comments)Read Original on HackerNews

mike_hearn•41 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•36 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•41 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:

https://huggingface.co/spaces/gemma-challenge/gemma-dashboar...

freedomben•about 1 hour ago

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•42 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•about 1 hour 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.

Fable 5 pushed Gemma 4 to 255 tok/s on WebGPU

⚡ Community Insights

Discussion (6 Comments)Read Original on HackerNews