MLX framework for Apple Silicon ML

22 repos

Machine learning libraries and applications built on MLX, Apple's framework for efficient ML on Apple Silicon devices. The cluster spans Python-based ML tools (22 repos), Swift/native iOS applications (8 repos), and integrations with popular models like Qwen and LLMs. Common themes include local inference, LLM deployment on macOS/iOS, and OpenAI-compatible APIs, reflecting a focus on bringing capable AI workloads to consumer Apple hardware without cloud dependency.

Python · 15

Swift · 6

Objective-C++ · 1

apple-silicon ·36,667

mlx ·36,667

llm ·34,367

macos ·28,845

openai-api ·26,927

inference-server ·23,184

vision-language-model ·8,462

local-ai ·7,769

local-llm ·7,084

qwen ·6,241

Related clusters

Quantized LLM Inference on Apple Silicon32 MLX and Apple Silicon ML Models39 Cluster 46223525 Cluster 46224014 Model Quantization and MLX Deployment10 Model Compression for Edge AI4

srvsngh99/Krill

Fast local LLM inference CLI for Apple Silicon. 1.57x faster than Ollama, 58% less memory.

Swift

372 commits

apocryphx/Apertura

A from-scratch Objective-C/MLX rebuild of Google's Gemma-4 for Apple Silicon — built to be…

Objective-C++

106 commits

jundot/omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the…

Python

21,611

2,517 commits

carloslfu/slotstream

Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming…

Swift

343

46 commits

nanguoyu/minirun-app

Run Kimi K3 (2.8 T parameters,1.56 TB) on iPhone 16 Pro? Weights stream from your SSD through a…

Swift

13 commits

walter-grace/expert-sniper

Run MoE models bigger than your RAM — SSD expert streaming on one Mac, or an Expert Network of…

Python

75 commits

jonready/vllm-ios

vLLM-style continuous batching for iPhone. Native Swift on MLX, no Python. The fastest multi-agent…

Swift

14 commits

DAWNCR0W/dflasher

CLI for building and testing DFlash-style speculative decoding draft models.

Python

6 commits

waybarrios/vllm-mlx

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native…

Python

1,566

597 commits

sethdford/gemma-realtime

Personalize Gemma 4 and make it real-time on Apple Silicon. Fine-tune on your conversations, serve…

Python

7 commits

Keith-CY/melix

Local-first AI runtime for Apple Silicon with CLI and macOS operator workflows for LoRA training,…

Swift

2,930 commits

ivanfioravanti/vlm-bakeoff

VLM bake-off — MLX vs GGUF: identical vision benchmarks across mlx-vlm and llama.cpp on Apple…

Python

24 commits

raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100%…

Python

3,725

2,017 commits

ARahim3/mlx-tune

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR…

Python

1,401

76 commits

szibis/mlx-flash

Run AI models too large for your Mac's memory — at near-full speed. Intelligent expert caching,…

Python

117 commits

dthinkr/mlx-lens

Mechanistic interpretability on Apple Silicon: steering vectors, residual capture, and SAE analysis…

Python

1 commits

youssofal/MTPLX

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No…

Python

2,173

1,184 commits

Greninja9257/LabLLM

A native macOS lab for teaching tiny language models to think — build the architecture, train the…

Swift

45 commits

cryptopoly/ChaosEngineAI

Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models.…

Python

578 commits

Blaizzy/mlx-vlm

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac…

Python

5,488

1,420 commits

dgrauet/ltx-2-mlx

Pure MLX port of LTX-2 (LTX-2.3 & LTX-2.5) for Apple Silicon — text/image/audio-to-video generation…

Python

111

300 commits

john-rocky/apple-silicon-llm-bench

Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI,…

Python

276 commits