Back to Topics Directory
Topic Hub

#mlx (30 Repositories)

Ranked open-source repositories tagged with #mlx, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

56.7%

Avg Review Latency

60.6h

Filter by language

30 repositories tagged #mlx

B TierPython 102

AVADSA25/codec

Open-Source Intelligent Command Layer

98.2%
Merge Rate
21h
First Review
100%
1st-Timers
0
Maintainers
B TierSwift 357 2 GFIs

PowerBeef/Vocello

Vocello: a local, private voice studio for Apple Silicon. Write a script, pick or describe a voice, and generate speech on-device, faster than realtime on an 8 GB M2 Mac mini. Native Swift + MLX, no Python. Mac app out now, iPhone beta on TestFlight. (Formerly QwenVoice.)

93.3%
Merge Rate
4d
First Review
100%
1st-Timers
0
Maintainers
A TierPython 3.5k 1 GFIs

raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

88.8%
Merge Rate
3d
First Review
53%
1st-Timers
15
Maintainers
A TierSwift 7.7k 1 GFIs

osaurus-ai/osaurus

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

82.6%
Merge Rate
3d
First Review
53%
1st-Timers
18
Maintainers
A TierSwift 1.1k

soniqo/speech-swift

AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML

93.7%
Merge Rate
2d
First Review
67%
1st-Timers
10
Maintainers
A TierPython 11.5k

debpalash/VoiceStudio

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

91.1%
Merge Rate
2d
First Review
100%
1st-Timers
4
Maintainers
A TierSwift 742

SharpAI/SwiftLM

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

86.0%
Merge Rate
6h
First Review
67%
1st-Timers
3
Maintainers
B TierRust 156

mlx-node/mlx-node

96.7%
Merge Rate
4d
First Review
100%
1st-Timers
0
Maintainers
A TierPython 2.3k

mflux-community/mflux

Apple MLX native implementations of state-of-the-art generative image & video models

75.0%
Merge Rate
5h
First Review
83%
1st-Timers
13
Maintainers
A TierPython 5.1k 34 GFIs

maziyarpanahi/openmed

Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0

74.2%
Merge Rate
2d
First Review
75%
1st-Timers
15
Maintainers
A TierZig 762

ddalcu/mlx-serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

70.1%
Merge Rate
7h
First Review
50%
1st-Timers
29
Maintainers
A TierSwift 162 11 GFIs

bitwize-ai/Logue

Privacy-first AI meeting notes & writing assistant for Mac — on-device transcription, smart minutes, action items & 60+ writing modes, running entirely on Apple Silicon

66.7%
Merge Rate
11h
First Review
50%
1st-Timers
5
Maintainers
A TierRust 34.5k

AlexsJones/llmfit

Hundreds of models & providers. One command to find what runs on your hardware.

62.1%
Merge Rate
20h
First Review
58%
1st-Timers
40
Maintainers
B TierPython 5.4k

Blaizzy/mlx-vlm

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

62.1%
Merge Rate
12h
First Review
47%
1st-Timers
60
Maintainers
B TierSwift 842

kennss/SiliconScope

Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking

76.5%
Merge Rate
3d
First Review
40%
1st-Timers
1
Maintainers
B TierC++ 28.2k

ml-explore/mlx

MLX: An array framework for Apple silicon

61.1%
Merge Rate
11h
First Review
51%
1st-Timers
64
Maintainers
B TierC++ 314

mudler/vllm.cpp

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (for example, RadixAttention, Cache-aware scheduling)

32.9%
Merge Rate
8h
First Review
14%
1st-Timers
13
Maintainers
B TierRust 223

morganlinton/Albatross

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud, your keys, one TUI. No black box.

78.9%
Merge Rate
3d
First Review
75%
1st-Timers
2
Maintainers
B TierPython 20.7k

jundot/omlx

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

56.4%
Merge Rate
1d
First Review
53%
1st-Timers
123
Maintainers
B TierPython 1.2k

lmstudio-ai/mlx-engine

LM Studio Apple MLX engine

50.0%
Merge Rate
<1h
First Review
0%
1st-Timers
1
Maintainers
B TierPython 6.8k

ml-explore/mlx-lm

Run LLMs with MLX

22.0%
Merge Rate
6h
First Review
22%
1st-Timers
45
Maintainers
B TierC++ 2.0k

ml-explore/mlx-swift

Swift API for MLX

38.1%
Merge Rate
8h
First Review
0%
1st-Timers
13
Maintainers
B TierPython 1.5k 1 GFIs

waybarrios/vllm-mlx

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

61.5%
Merge Rate
12d
First Review
34%
1st-Timers
20
Maintainers
C TierSwift 761

Blaizzy/mlx-audio-swift

A modular Swift SDK for audio processing with MLX on Apple Silicon

33.3%
Merge Rate
12d
First Review
0%
1st-Timers
2
Maintainers
C TierTypeScript 51.8k

jamiepine/voicebox

The open-source AI voice studio. Clone, dictate, create.

36.4%
Merge Rate
3d
First Review
32%
1st-Timers
73
Maintainers
C TierPython 828

jjang-ai/vmlx

vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

14.6%
Merge Rate
17d
First Review
18%
1st-Timers
4
Maintainers
D TierRust 310

Epistates/pmetal

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierSwift 326

PicoMLX/PicoMLXServer

The easiest way to run the fastest MLX-based LLMs locally

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 340

Mininglamp-AI/cider

W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA speedup, built as MLX custom primitives.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 499

harperreed/photo-similarity-search

Super simple MLX (apple silicon) CLIP based photo similarity web app

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
Best Mlx Open Source Repositories & C-Rank™ | GetMerged