waybarrios/vllm-mlx
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.
Platform-specific configuration:
{
"mcpServers": {
"vllm-mlx": {
"command": "npx",
"args": [
"-y",
"vllm-mlx"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Loading reviews...