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.
- Stars
- 261
- Forks
- 12
- Open issues
- 0
- Last push
- 1mo ago
q38rocm star history
+1 this week
About q38rocm
q38rocm is a free, open-source AI inference tool by julianmb, written mainly in Python. 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. It has 261 GitHub stars and 12 forks, and was last updated 1mo ago. GitHub doesn't detect a standard license, so check the repository before using it commercially.
- License
- Not detected
- Commercial use
- No license
- Language
- Python
- Stars
- 261
- Last update
- 1mo ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Not stated
Similar free tools
llama.cpp132k stars · LLM inference in C/C++
lucebox3.0k stars · LLM speculative inference server for heterogeneous hardware & consumer GPUs
strix-halo-llamacpp220 stars · Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.
node-llama-cpp2.2k stars · Run AI models locally with node.js bindings for llama.cpp.
ai-infra-book7.0k stars · 《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
halogen-flash-server1.1k stars · The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)
q38rocm FAQ
Can I use q38rocm commercially?
Unclear. No license was detected, which legally means all rights are reserved. Ask the author before using it commercially. This is a plain-English summary, not legal advice.
Is q38rocm free?
Yes. q38rocm is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.
Does q38rocm run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does q38rocm need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is q38rocm still maintained?
It was last updated 1mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to q38rocm?
Similar free, open-source tools include llama.cpp, lucebox, strix-halo-llamacpp, node-llama-cpp.
Maintain q38rocm?
Add this badge to your README to show it's featured on FreeAIRepo.
[](https://www.freeairepo.com/repo/julianmb/q38rocm)