Run Qwen3.8-27B locally on Windows with one NVIDIA RTX GPU: chat and an OpenAI-compatible API. On an RTX 5090 the fastest model averaged 2,298 tok/s on our own JSONL edit task (one request at a time, thinking off, v0.1.4).
Repository Index
132,241 visible repositories in the index
169–172 of 172 · Most stars
Gemini CLI wrapper to serve Gemini models through an OpenAI-compatible API
- gemini-ai
Claude Code Gateway for Kimi, GLM, DeepSeek, and OpenRouter
- claude-code
- claude-code-alternative
- claude-code-api
- claude-code-free
Publish Claude Code usage telemetry to MQTT for Home Assistant (Clawdmeter-compatible mood/burn-rate sensors)