#strix-halo (5 Repositories)
Ranked open-source repositories tagged with #strix-halo, scored by pull request acceptance likelihood and maintainer engagement velocity.
60.6%
7.6h
5 repositories tagged #strix-halo
Yamz-Labs/kyojin
Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini PC.
gufo-org/gufo
The Open Source Strix Halo AI engine. Qwen Flash Next Q4_K_XL: 1,773.82pp, 65.25tg single user, 184.74 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2
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.
hogeheer499-commits/strix-halo-guide
Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
Soulmate-Halo/heterogeneous-gpu-pd-lab
使用稠密算力卡对稀疏大显存主机进行加速，主机包括 AI Max+ 395、M3 512G、DGX Spark 等。