Comment by mercutio2

12 days ago

What toolchain are you going to use with the local model? I agree that’s a Strong model, but it’s so slow for be with large contexts I’ve stopped using it for coding.

6 comments

mercutio2

Reply
embedding-shape  12 days ago

I have my own agent harness, and the inference backend is vLLM.

  • mercutio2  11 days ago

    Can you tell me more about your agent harness? If it’s open source, I’d love to take it for a spin.

    I would happily use local models if I could get them to perform, but they’re super slow if I bump their context window high, and I haven’t seen good orchestrators that keep context limited enough.

  • storystarling  12 days ago

    Curious how you handle sharding and KV cache pressure for a 120b model. I guess you are doing tensor parallelism across consumer cards, or is it a unified memory setup?

    • embedding-shape  12 days ago

      I don't, fits on my card with the full context, I think the native MXFP4 weights takes ~70GB of VRAM (out of 96GB available, RTX Pro 6000), so I still have room to spare to run GPT-OSS-20B alongside for smaller tasks too, and Wayland+Gnome :)

      2 replies →