GitHub - jjang-ai/vmlx: vMLX - Home of JANG_Q - No other MLX inferencer can do this. Cont Batch, Prefix, Paged, KV Cache Quant, VL - Powers MLX Studio. Image gen/edit, OpenAI/Anth

Local AI Engine for Apple Silicon

Run LLMs, VLMs, and image generation models entirely on your Mac.
OpenAI + Anthropic 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 2-bit destroys MLX 4-bit on MiniMax M2.5:

Quantization MMLU (200q) Size

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 critical layers at higher precision. Scores at jangq.ai. Models at JANGQ-AI.


Chat with any MLX model -- thinking mode, streaming, and syntax highlighting	Agentic chat with full coding capabilities -- tool use and structured output

Quickstart

Install from PyPI

Published on PyPI as vmlx -- install and run in one command:

# 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

Note: On macOS 14+, bare pip install fails with "externally-managed-environment". Use uv, pipx, or a venv.

Your local AI server is now running at http://0.0.0.0:8000 with an OpenAI + Anthropic compatible API. Works with any model from mlx-community -- thousands of models ready to go.

Or download the desktop app

Get MLX Studio -- a native macOS app with chat UI, model management, image generation, and developer tools. No terminal required. Just download the DMG and drag to Applications.

Use with OpenAI SDK

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="not-needed")
response = client.chat.completions.create(
    model="local",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)
for chunk in response:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

Use with Anthropic SDK

import anthropic

client = anthropic.Anthropic(base_url="http://localhost:8000/v1", api_key="not-needed")
message = client.messages.create(
    model="local",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
print(message.content[0].text)

Use with curl

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

Model Support

vMLX runs any MLX model. Point it at a HuggingFace repo or local path and go.

Type	Models
Text LLMs	Qwen 2/2.5/3/3.5, Llama 3/3.1/3.2/3.3/4, Mistral/Mixtral, Gemma 3, Phi-4, DeepSeek, GLM-4, MiniMax, Nemotron, StepFun, and any mlx-lm model
Vision LLMs	Qwen-VL, Qwen3.5-VL, Pixtral, InternVL, LLaVA, Gemma 3n
MoE Models	Qwen 3.5 MoE (A3B/A10B), Mixtral, DeepSeek V2/V3, MiniMax M2.5, Llama 4
Hybrid SSM	Nemotron-H, Jamba, GatedDeltaNet (Mamba + Attention)
Image Gen	Flux Schnell/Dev, Z-Image Turbo (via mflux)
Image Edit	Qwen Image Edit (via mflux)
Embeddings	Any mlx-lm compatible embedding model
Reranking	Cross-encoder reranking models
Audio	Kokoro TTS, Whisper STT (via mlx-audio)

Features

Inference Engine

Feature	Description
Continuous Batching	Handle multiple concurrent requests efficiently
Prefix Cache	Reuse KV states for repeated prompts -- makes follow-up messages instant
Paged KV Cache	Block-based caching with content-addressable deduplication
KV Cache Quantization	Compress cached states to q4/q8 for 2-4x memory savings
Disk Cache (L2)	Persist prompt caches to SSD -- survives server restarts
Block Disk Cache	Per-block persistent cache paired with paged KV cache
Speculative Decoding	Small draft model proposes tokens for 20-90% speedup
JIT Compilation	`mx.compile` Metal kernel fusion (experimental)
Hybrid SSM Support	Mamba/GatedDeltaNet layers handled correctly alongside attention

5-Layer Cache Architecture

Request -> Tokens
    |
L1: Memory-Aware Prefix Cache (or Paged Cache)
    | miss
L2: Disk Cache (or Block Disk Store)
    | miss
Inference -> float16 KV states
    |
KV Quantization -> q4/q8 for storage
    |
Store back into L1 + L2

Tool Calling

Auto-detected parsers for every major model family:

qwen - llama - mistral - hermes - deepseek - glm47 - minimax - nemotron - granite - functionary - xlam - kimi - step3p5

Reasoning / Thinking Mode

Auto-detected reasoning parsers that extract <think> blocks:

qwen3 (Qwen3, QwQ, MiniMax, StepFun) - deepseek_r1 (DeepSeek R1, Gemma 3, GLM, Phi-4) - openai_gptoss (GLM Flash, GPT-OSS)

Audio

Feature	Description
Text-to-Speech	Kokoro TTS via mlx-audio -- multiple voices, streaming output
Speech-to-Text	Whisper STT via mlx-audio -- transcription and translation

Image Generation & Editing

Generate and edit images locally with Flux models via mflux.

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

Generation API

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
  }'

# Python (OpenAI SDK)
response = client.images.generate(
    model="schnell",
    prompt="A cat astronaut floating in space",
    size="1024x1024",
    n=1,
)

Editing API

# 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
  }'

# Python
import base64
with open("source.png", "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode()

response = requests.post("http://localhost:8000/v1/images/edits", json={
    "model": "flux-kontext",
    "prompt": "Make the sky purple",
    "image": image_b64,
    "size": "1024x1024",
    "strength": 0.8,
})

Supported Image Models

Generation Models:

Model	Steps	Speed	Memory
Flux Schnell	4	Fastest	~6-24 GB
Z-Image Turbo	4	Fast	~6-24 GB
Flux Dev	20	Slow	~6-24 GB

Editing Models:

Model	Steps	Type	Memory
Qwen Image Edit	28	Instruction-based editing	~54 GB

API Reference

Endpoints

Method	Path	Description
`POST`	`/v1/chat/completions`	OpenAI Chat Completions API (streaming + non-streaming)
`POST`	`/v1/messages`	Anthropic Messages API
`POST`	`/v1/responses`	OpenAI Responses API
`POST`	`/v1/completions`	Text completions
`POST`	`/v1/images/generations`	Image generation
`POST`	`/v1/images/edits`	Image editing (Qwen Image Edit)
`POST`	`/v1/embeddings`	Text embeddings
`POST`	`/v1/rerank`	Document reranking
`POST`	`/v1/audio/transcriptions`	Speech-to-text (Whisper)
`POST`	`/v1/audio/speech`	Text-to-speech (Kokoro)
`GET`	`/v1/models`	List loaded models
`GET`	`/v1/cache/stats`	Cache statistics
`GET`	`/health`	Server health check

curl Examples

Chat completion (streaming)

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
  }'

Chat completion with thinking mode

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
  }'

Tool calling

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"]
        }
      }
    }]
  }'

Anthropic Messages API

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!"}]
  }'

Embeddings

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

Text-to-speech

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

Speech-to-text

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

Image generation

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

Reranking

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"
    ]
  }'

Cache stats

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

Health check

curl http://localhost:8000/health

Desktop App

vMLX includes a native macOS desktop app (MLX Studio) with 5 modes:

Mode	Description
Chat	Conversation interface with chat history, thinking mode, tool calling, agentic coding
Server	Manage model sessions -- start, stop, configure, monitor
Image	Text-to-image generation and image editing with Flux, Kontext, Qwen, and Fill models
Tools	Model converter, GGUF-to-MLX, inspector, diagnostics
API	Live endpoint reference with copy-pasteable code snippets


Image generation and editing with Flux models	Developer tools -- model conversion and diagnostics

Anthropic Messages API endpoint -- full compatibility	GGUF to MLX conversion -- bring your own models

Download

Get the latest DMG from MLX Studio Releases, or build from source:

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

Menu Bar

vMLX lives in your menu bar showing all running models, GPU memory usage, and quick controls.

Advanced Quantization

vMLX supports standard MLX quantization (4-bit, 8-bit uniform) out of the box. For users who want to push further, JANG adaptive mixed-precision assigns different bit widths to different layer types -- attention gets more bits, MLP layers get fewer -- achieving better quality at the same model size.

JANG Profiles

Profile	Attention	Embeddings	MLP	Avg Bits	Use Case
`JANG_2M`	8-bit	4-bit	2-bit	~2.5	Balanced compression
`JANG_2L`	8-bit	6-bit	2-bit	~2.7	Quality 2-bit
`JANG_3M`	8-bit	3-bit	3-bit	~3.2	Recommended
`JANG_4M`	8-bit	4-bit	4-bit	~4.2	Standard quality
`JANG_6M`	8-bit	6-bit	6-bit	~6.2	Near lossless

Convert

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

Pre-quantized JANG models are available at JANGQ-AI on HuggingFace.

CLI Commands

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

Configuration

Server Options

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
  --cors-origins "*"            # CORS allowed origins

Quantization Options

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

Image Generation & Editing Options

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

Audio Options

TTS and STT require the mlx-audio package:

pip install mlx-audio

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

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

Optional Dependencies

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

Architecture

+--------------------------------------------+
|          Desktop App (Electron)             |
|   Chat | Server | Image | Tools | API      |
+--------------------------------------------+
|          Session Manager (TypeScript)       |
|   Process spawn | Health monitor | Tray     |
+--------------------------------------------+
|         vMLX Engine (Python / FastAPI)       |
|  +--------+  +---------+  +-----------+    |
|  |Simple  |  | Batched |  | ImageGen  |    |
|  |Engine  |  | Engine  |  | Engine    |    |
|  +---+----+  +----+----+  +-----+-----+    |
|      |            |              |          |
|  +---+------------+--+    +-----+-----+    |
|  | mlx-lm / mlx-vlm  |    |  mflux    |    |
|  +--------+-----------+    +-----------+    |
|           |                                 |
|  +--------+----------------------------+    |
|  |       MLX Metal GPU Backend          |    |
|  | quantized_matmul | KV cache | SDPA   |    |
|  +--------------------------------------+    |
+--------------------------------------------+
|  L1: Prefix Cache (Memory-Aware / Paged)    |
|  L2: Disk Cache (Persistent / Block Store)  |
|  KV Quant: q4/q8 at storage boundary       |
+--------------------------------------------+

Contributing

Contributions are welcome. Here is how to set up a development environment:

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

Project Structure

vmlx/
  vmlx_engine/          # Python inference engine (FastAPI server)
  panel/                # Electron desktop app (React + TypeScript)
    src/main/           # Electron main process
    src/renderer/       # React frontend
    src/preload/        # IPC bridge
  tests/                # Python test suite
  assets/               # Screenshots and logos

Guidelines

Run the full test suite before submitting PRs
Follow existing code style and patterns
Include tests for new features
Update documentation for user-facing changes

License

Apache License 2.0 -- see LICENSE.

Built by Jinho Jang (eric@jangq.ai)
JANGQ AI • PyPI • GitHub • Downloads

한국어 (Korean)

vMLX — Apple Silicon을 위한 로컬 AI 엔진

Mac에서 LLM, VLM, 이미지 생성 및 편집 모델을 완전히 로컬로 실행하세요. OpenAI + Anthropic 호환 API. 클라우드 없음. API 키 불필요. 데이터가 기기를 떠나지 않습니다.

빠른 시작

pip install vmlx
vmlx serve mlx-community/Llama-3.2-3B-Instruct-4bit

주요 기능

기능	설명
텍스트 생성	MLX 및 JANG 형식의 LLM 추론
비전-언어 모델	이미지 + 텍스트 멀티모달 추론
이미지 생성	Flux Schnell/Dev, Z-Image Turbo (mflux 기반)
이미지 편집	Qwen Image Edit (텍스트 지시 기반 이미지 편집)
5단계 캐싱	프리픽스, 페이지드, KV 양자화, 디스크, 메모리 인식 캐시
연속 배칭	다중 동시 요청 처리
에이전트 도구	30개 내장 도구 (파일, 웹 검색, Git, 터미널)
OpenAI API	/v1/chat/completions, /v1/images/generations, /v1/images/edits
Anthropic API	/v1/messages (스트리밍, 도구 호출, 시스템 프롬프트)

이미지 생성

pip install vmlx[image]
vmlx serve schnell          # 빠른 생성 (4 단계)
vmlx serve dev              # 고품질 생성 (20 단계)

이미지 편집

vmlx serve qwen-image-edit  # 텍스트 지시 기반 이미지 편집

# 이미지 편집 API
curl http://localhost:8000/v1/images/edits \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-edit",
    "prompt": "배경을 해질녘으로 변경",
    "image": "<base64 인코딩된 이미지>",
    "size": "1024x1024",
    "strength": 0.8
  }'

데스크톱 앱 (MLX Studio)

macOS 네이티브 데스크톱 앱으로 5가지 모드를 제공합니다:

모드	설명
채팅	대화 인터페이스, 채팅 기록, 도구 호출, 에이전트 코딩
서버	모델 세션 관리 — 시작, 정지, 설정, 모니터링
이미지	텍스트-이미지 생성 및 이미지 편집 (Flux, Qwen 모델)
도구	모델 변환기, GGUF-MLX 변환, 진단
API	실시간 엔드포인트 참조 및 코드 스니펫

설치

pip install vmlx              # 기본: 텍스트 LLM, VLM, 임베딩
pip install vmlx[image]       # + 이미지 생성/편집 (mflux)
pip install vmlx[jang]        # + JANG 양자화 도구
pip install vmlx[audio]       # + TTS/STT (mlx-audio)

라이선스

Apache License 2.0 — LICENSE 참조.

개발자: 장진호 (eric@jangq.ai)
JANGQ AI • Ko-fi로 후원하기

Name		Name	Last commit message	Last commit date
Latest commit History 248 Commits
assets		assets
docs		docs
notes		notes
panel		panel
tests		tests
vmlx_engine		vmlx_engine
.gitignore		.gitignore
CHANGELOG.md		CHANGELOG.md
LICENSE		LICENSE
README.md		README.md
latest.json		latest.json
pyproject.toml		pyproject.toml
pytest.ini		pytest.ini

Quantization	MMLU (200q)	Size
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

Folders and files

Latest commit

History

Repository files navigation

Local AI Engine for Apple Silicon

Quickstart

Install from PyPI

Or download the desktop app

Use with OpenAI SDK

Use with Anthropic SDK

Use with curl

Model Support

Features

Inference Engine

5-Layer Cache Architecture

Tool Calling

Reasoning / Thinking Mode

Audio

Image Generation & Editing

Generation API

Editing API

Supported Image Models

API Reference

Endpoints

curl Examples

Desktop App

Download

Menu Bar

Advanced Quantization

JANG Profiles

Convert

CLI Commands

Configuration

Server Options

Quantization Options

Image Generation & Editing Options

Audio Options

Optional Dependencies

Architecture

Contributing

Project Structure

Guidelines

License

한국어 (Korean)

vMLX — Apple Silicon을 위한 로컬 AI 엔진

빠른 시작

주요 기능

이미지 생성

이미지 편집

데스크톱 앱 (MLX Studio)

설치

라이선스

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases 6

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Packages