Skip to content
@peonist-ai

Peonist.ai

Work, work.

Popular repositories Loading

  1. halogen-flash-server halogen-flash-server Public

    Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

    Shell 1.2k 82

  2. halogen-server halogen-server Public

    The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)

    Python 157 8

  3. crucible crucible Public

    MoE expert compression toolkit — prune, merge, and forge specialist models for local inference.

    Python 13

Repositories

Showing 3 of 3 repositories
  • halogen-flash-server Public

    Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

    peonist-ai/halogen-flash-server's past year of commit activity
    Shell 1,228 81 24 1 Updated Nov 5, 2026
  • crucible Public

    MoE expert compression toolkit — prune, merge, and forge specialist models for local inference.

    peonist-ai/crucible's past year of commit activity
    Python 13 Apache-2.0 0 0 9 Updated Nov 3, 2026
  • halogen-server Public

    The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)

    peonist-ai/halogen-server's past year of commit activity
    Python 157 8 6 0 Updated Sep 14, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Python Shell