jjang-ai / vmlx
vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm
Why this job: says: gguf; topics: mlx
What it does
Self-hosted inference server for LLMs, VLMs, and image generation on Apple Silicon. OpenAI + Anthropic + Ollama compatible HTTP API. Self-hosted; no third-party API keys required. Native MTP artifact detection and family-specific cache policy gates keep speculative/cache settings explicit and model-safe.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 913
- +7 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- Mac
- From the latest release
- Latest version
- v1.6.84
- Released 2 days ago
- Built with
- Python
- 82% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 71% closed
- 56 still open
- Pull requests
- 111 merged
- 12 waiting
- Releases
- 138
- 30+ in the last year
- No contributing guide
- No security policy
- No code of conduct
More: download files, languages, topics and project record
Languages
- Python 82%
- TypeScript 15%
- JavaScript 2%
- Shell <1%
Topics
- llm
- lmstudio
- macbook
- mlx
- mlxllm
- mlxstudio
- anthropic-api
- kvcache-compression
- kvcache-optimization
- kvcache-reuse
- mcp-server
- openai-api
Project record
- JobLocal LLMs
- StatusListed
- Commits5,904
- Forks101
- Watching6
- Stars in 28 days+26
- CreatedFeb 18, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026