# Recommended: uv (fast, no venv hassle)
brew install uv
uv tool install vmlx
vmlx serve mlx-community/Qwen3-8B-4bit

# Or: pipx (isolates from system Python)
brew install pipx
pipx install vmlx
vmlx serve mlx-community/Qwen3-8B-4bit

# Or: pip in a virtual environment
python3 -m venv ~/.vmlx-env && source ~/.vmlx-env/bin/activate
pip install vmlx
vmlx serve mlx-community/Qwen3-8B-4bit

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "local",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

pip install vmlx[image]

# Image generation
vmlx serve schnell                    # or dev, z-image-turbo
vmlx serve ~/.mlxstudio/models/image/flux1-schnell-4bit

# Image editing
vmlx serve qwen-image-edit            # instruction-based editing

curl http://localhost:8000/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
    "model": "schnell",
    "prompt": "A cat astronaut floating in space with Earth in the background",
    "size": "1024x1024",
    "n": 1
  }'

# Edit an image with a text prompt (Flux Kontext / Qwen Image Edit)
curl http://localhost:8000/v1/images/edits \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-kontext",
    "prompt": "Change the background to a sunset",
    "image": "<base64-encoded-image>",
    "size": "1024x1024",
    "strength": 0.8
  }'

# All models accessible through the gateway
curl http://localhost:8080/v1/chat/completions \
  -d '{"model": "Qwen3.5-122B", "messages": [{"role": "user", "content": "Hi"}]}'

# Works with Ollama CLI too
OLLAMA_HOST=http://localhost:8080 ollama run Qwen3.5-122B

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "local",
    "messages": [{"role": "user", "content": "Explain quantum computing in 3 sentences."}],
    "stream": true,
    "temperature": 0.7
  }'

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "local",
    "messages": [{"role": "user", "content": "Solve: what is 23 * 47?"}],
    "enable_thinking": true,
    "stream": true
  }'

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "local",
    "messages": [{"role": "user", "content": "What is the weather in Tokyo?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {"type": "string", "description": "City name"}
          },
          "required": ["location"]
        }
      }
    }]
  }'

curl http://localhost:8000/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: not-needed" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "local",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

curl http://localhost:8000/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "model": "local",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

curl http://localhost:8000/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kokoro",
    "input": "Hello, welcome to vMLX!",
    "voice": "af_heart"
  }' --output speech.wav

curl http://localhost:8000/v1/audio/transcriptions \
  -F file=@audio.wav \
  -F model=whisper

curl http://localhost:8000/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
    "model": "schnell",
    "prompt": "A mountain landscape at sunset",
    "size": "1024x1024"
  }'

curl http://localhost:8000/v1/rerank \
  -H "Content-Type: application/json" \
  -d '{
    "model": "local",
    "query": "What is machine learning?",
    "documents": [
      "ML is a subset of AI",
      "The weather is sunny today",
      "Neural networks learn from data"
    ]
  }'

curl http://localhost:8000/v1/cache/stats

curl http://localhost:8000/health

git clone https://github.com/jjang-ai/vmlx.git
cd vmlx/panel
npm install && npm run build
npx electron-builder --mac dmg

pip install vmlx[jang]

# Standard MLX quantization
vmlx convert my-model --bits 4

# JANG adaptive quantization
vmlx convert my-model --jang-profile JANG_3M

# Activation-aware calibration (better at 2-3 bit)
vmlx convert my-model --jang-profile JANG_2L --calibration-method activations

# Serve the converted model
vmlx serve ./my-model-JANG_3M --continuous-batching --use-paged-cache

vmlx serve <model>              # Start inference server
vmlx convert <model> --bits 4   # MLX uniform quantization
vmlx convert <model> -j JANG_3M # JANG adaptive quantization
vmlx info <model>               # Model metadata and config
vmlx doctor <model>             # Run diagnostics
vmlx bench <model>              # Performance benchmarks

vmlx serve <model> \
  --host 0.0.0.0 \              # Bind address (default: 0.0.0.0)
  --port 8000 \                 # Port (default: 8000)
  --api-key sk-your-key \       # Optional API key authentication
  --continuous-batching \       # Enable concurrent request handling
  --enable-prefix-cache \       # Reuse KV states for repeated prompts
  --use-paged-cache \           # Block-based KV cache with dedup
  --kv-cache-quantization q8 \  # Quantize cache: q4 or q8
  --enable-disk-cache \         # Persist cache to SSD
  --enable-jit \                # JIT Metal kernel compilation
  --tool-call-parser auto \     # Auto-detect tool call format
  --reasoning-parser auto \     # Auto-detect thinking format
  --log-level INFO \            # Logging: DEBUG, INFO, WARNING, ERROR
  --max-model-len 8192 \        # Max context length
  --speculative-model <model> \ # Draft model for speculative decoding
  --enable-pld \                # Prompt Lookup Decoding — no draft model, best for code/JSON/schemas
  --cors-origins "*"            # CORS allowed origins

vmlx convert <model> \
  --bits 4 \                    # Uniform quantization bits: 2, 3, 4, 6, 8
  --group-size 64 \             # Quantization group size (default: 64)
  --output ./output-dir \       # Output directory
  --jang-profile JANG_3M \      # JANG mixed-precision profile
  --calibration-method activations  # Activation-aware calibration

pip install vmlx[image]

# Generation models
vmlx serve schnell \            # or dev, z-image-turbo
  --image-quantize 4 \          # Quantization: 4, 8 (omit for full precision)
  --port 8001

# Editing models
vmlx serve qwen-image-edit \    # Instruction-based editing (full precision only)
  --port 8001

# Local model directory
vmlx serve ~/.mlxstudio/models/image/FLUX.1-schnell-mflux-4bit

pip install mlx-audio

# TTS: serve Kokoro model
vmlx serve kokoro --port 8002

# STT: serve Whisper model
vmlx serve whisper --port 8003

pip install vmlx              # Core: text LLMs, VLMs, embeddings, reranking
pip install vmlx[image]       # + Image generation (mflux)
pip install vmlx[jang]        # + JANG quantization tools
pip install vmlx[dev]         # + Development/testing tools
pip install vmlx[image,jang]  # Multiple extras

git clone https://github.com/jjang-ai/vmlx.git
cd vmlx

# Python engine
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev,jang,image]"
pytest tests/ -k "not Async"    # 2000+ tests

# Electron desktop app
cd panel && npm install
npm run dev                      # Development mode with hot reload
npx vitest run                   # 1545+ tests