Skip to main content

Tag · 4 repos

strix-halo

Repositories carrying the strix-halo tag.

Exact tag match4 sample repositories
419
Soulmate-Halo/heterogeneous-gpu-pd-lab

Accelerate sparse, high-memory hosts with dense-compute cards. Hosts include AI Max+ 395, M3 512G, DGX Spark, and others.

PythonLocal LLMs
531
Osmantic/ODS

ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

PythonLocal LLMsAI Agents
4790
rulith-dev/rulith-inference

Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a manager, and a desktop app.

PythonLocal LLMsMobile & Desktop Apps
5002
julianmb/q38rocm

Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.

PythonLocal LLMsLLM Inference & Serving