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.
- amd
- gfx1151
- gpu-inference
- hip
108,094 visible repositories in the index
1–3 of 3 · Most stars
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.
Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH, no root required.
Shell wrapper for OpenAI's ChatGPT, Whisper, and TTS. Features LocalAI, Ollama, Gemini, Anthropic, and more.