vmlx

by jjang-ai · Python · ★ 422

vMLX - Home of JANG_Q - Cont Batch, Prefix, Paged, KV Cache Quant, VL - Powers MLX Studio. Image gen/edit, OpenAI/Anth

#anthropic-api#kvcache-compression#kvcache-optimization#kvcache-reuse#llm#lmstudio#macbook#mcp-server#mlx#mlxllm#mlxstudio#omlx#omlx-alternative#openai-api#openclaw#openclaw-agent#persistent-memory#prefix-cache#vmlx

Install

pip install git+https://github.com/jjang-ai/vmlx.git

Claude Desktop config

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "vmlx": {
      "command": "uvx",
      "args": [
        "git+https://github.com/jjang-ai/vmlx.git"
      ]
    }
  }
}

From the README

Local AI Engine for Apple Silicon Run LLMs, VLMs, and image generation models entirely on your Mac. OpenAI + Anthropic + Ollama compatible API. No cloud. No API keys. No data leaving your machine. Quickstart • Models • Features • Image Gen • API • Desktop App • JANG • CLI • Config • Contributing • 한국어 |---|---| > | **JANG\_2L (2-bit)** | **74%** | **89 GB** | > | MLX 4-bit | 26.5% | 120 GB | > | MLX 3-bit | 24.5% | 93 GB | > | MLX 2-bit | 25% | 68 GB | > > Adaptive mixed-precision keeps critica…

Read full README on GitHub →

💡 Need a managed MCP host?

Try Claude Pro for the smoothest MCP experience, or browse our cloud-hosted servers.

Related developer tools servers

everything-claude-code

affaan-m

★ 170,676

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Developer Tools · JavaScript