strix-halo repositories
Trending repositories tagged strix-halo, ranked by trending score. Updated daily.
-
1
mw00/project-maya
Run GLM-5.3 (744B), DeepSeek-V4.1-Flash (748B), MiniMax-M3.1-Flash (428B), GLM-5.3-Flash (321B) and Hy4-Flash (220B) on your own GPUs - from 8 GB of VRAM, NVIDIA and AMD, one dashboard, OpenAI- and Anthropic-compatible API.
GitHub · Cuda · 3,209 stars · 456 forks · +91 stars in 24 hours · Trending score 3.80
-
2
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.
GitHub · Python · 7,900 stars · 1,125 forks · +35 stars in 24 hours · Trending score 2.90
-
3
gufo-org/gufo
The open-source AI engine for AMD Strix Halo. Text, embeddings, speech, image and video models in one binary, with OpenAI-compatible APIs, caching for coding agents and model extensions. Linux and Windows.
GitHub · C++ · 1,247 stars · 217 forks · +15 stars in 24 hours · Trending score 2.59
-
4
peonist-ai/halogen-flash-server
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.
GitHub · Shell · 1,417 stars · 104 forks · +14 stars in 24 hours · Trending score 2.50
-
5
peonist-ai/halogen-server
The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)
GitHub · Python · 166 stars · 9 forks · +29 stars in 24 hours · Trending score 2.38
-
6
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.
GitHub · Python · 56 stars · 6 forks · +22 stars in 24 hours · Trending score 2.30
-
7
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。
GitHub · C++ · 1,297 stars · 203 forks · +8 stars in 24 hours · Trending score 2.23
-
8
hyukudan/strix-halo-engine-lab
C++ inference on AMD Strix Halo (one node or USB4 pair) and NVIDIA RTX PRO 6000. Engines for Qwen3.8-Flash-Next, Qwen3.8-27B, DeepSeek V4.1 Flash, GLM-5.3 Flash, Hy4-flash, MiniMax M3.1 Flash, MiniMax H3, MiniMax-H3-Image and Nemotron 3.5 Bolt E4B.
GitHub · C++ · 39 stars · 8 forks · +2 stars in 24 hours · Trending score 1.32
-
9
Yamz-Labs/kyojin
Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVIDIA RTX and Apple Mac. OpenAI API, built on ExLlamaV3.
GitHub · Python · 245 stars · 39 forks · +3 stars in 24 hours · Trending score 1.26
-
10
IIIIIllllIIIIIlllll/Qwenox
An inference framework customized for AI MAX 395, compatible with both Linux and Windows, and supports deploying only qwen3.8-flash-next. This project is for reference and learning purposes only. 为AI MAX 395定制的推理框架,Linux和Windows通用,只能部署qwen3.8-flash-next。本项目仅供参考学习使用。
GitHub · C++ · 154 stars · 31 forks · +3 stars in 24 hours · Trending score 1.22
-
11
asf0/libstrix
Fast vLLM on AMD Strix Halo: one docker command for Qwen, Gemma, LFM and more, up to 31x faster prefill and ~2x decode vs stock vLLM at long context.
GitHub · Python · 23 stars · 1 forks · +4 stars in 24 hours · Trending score 1.14
-
12
JeremiahM37/strix-halo-sglang
SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)
GitHub · Python · 42 stars · 10 forks · 0 stars in 24 hours · Trending score 0.83
-
13
jaedync/crucible-strix-halo
Run Qwen3.8-Flash-Next on one AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). EXL3 4.05 and 3.05 bpw packs, own ROCm/HIP kernels, OpenAI-compatible server, 4 sessions of 262K context, setup guide included.
GitHub · Python · 35 stars · 7 forks · 0 stars in 24 hours · Trending score 0.78
-
14
outerreaches/moonshine
Run the official Kimi K3 MoE checkpoint on one 128 GB AMD Strix Halo box. ROCm-resident static weights, MXFP4 experts streamed from NVMe via io_uring. C engine, chat client, OpenAI-compatible server. Very experimental.
GitHub · C · 9 stars · 0 forks · +2 stars in 24 hours · Trending score 0.73
-
15
julianmb/halofpx
High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), bleeding-edge RDNA 3.5 Wave64/ROCmFP4 kernels, and silicon-tuned profiles.
GitHub · Python · 96 stars · 4 forks · +2 stars in 24 hours · Trending score 0.72
-
16
SnowLLM/SnowLLM
Your Ryzen AI Max is running at half speed. SnowLLM: up to 9x faster prefill and 2x faster decode than llama.cpp on the same GGUF. Qwen3.6-35B-A3B, Qwen3.8-Flash-Next, DeepSeek-V4-Flash.
GitHub · Python · 21 stars · 2 forks · 0 stars in 24 hours · Trending score 0.56
-
17
jtsylve/hgn-spec
Clean-room spec of halogen's HGN weight format and quants, with test vectors and porting guides.
GitHub · 11 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46
-
18
jyatesdotdev/strix-rdma
General RDMA transport between two Strix Halo hosts over Thunderbolt/USB4 NHI DMA rings: a native software-verbs provider with a zero-copy data plane, plus the USB4STREAM backport it builds on
GitHub · C · 6 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46
-
19
doctomoe2019/strix-dual-exp
Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing link, and gufo TP2 integration
GitHub · C · 17 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46
-
20
franzmoca/ds41-gufo-extension
DeepSeek V4.1 Flash for Gufo on AMD Strix Halo: DSpark drafting, vision, tool calls and SSD expert streaming
GitHub · C++ · 8 stars · 2 forks · 0 stars in 24 hours · Trending score 0.40
-
21
1bit-MONSTER/engine
One binary to rule them all: model-agnostic local LLM inference for AMD Strix Halo (Ryzen AI MAX+ 395) on Linux. Radeon 8060S iGPU (gfx1151) via HRX + our HIP kernels, XDNA 2 NPU via our NPU runtime, inside Lemonade Server with an OpenAI-compatible API. Qwen3.8, ZAYA1, BitNet b1.58, any GGUF. Apache-2.0.
GitHub · C++ · 10 stars · 2 forks · 0 stars in 24 hours · Trending score 0.38
-
22
Hal0ai/hal0
Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + systemd.
GitHub · Python · 87 stars · 13 forks · 0 stars in 24 hours · Trending score 0.33
-
23
julianmb/haloq38flash
qwen3.8-flash-next on strix halo — 91g quant, 56 tok/s, 262k context, receipts included
GitHub · Shell · 28 stars · 2 forks · 0 stars in 24 hours · Trending score 0.32
-
24
pepuscz/strix-halo-llm
DeepSeek-V4.1-Flash (1M context) and GLM-5.3-Flash on a BOSGAME M5 (Ryzen AI Max+ 395, Radeon 8060S, 128 GiB) with two RX 7900 XTX over OCuLink: pinned Ansible recipes and measured results. Also the M5-only Qwen and DeepSeek setups.
GitHub · Python · 31 stars · 2 forks · 0 stars in 24 hours · Trending score 0.20