The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
☆2,727Nov 7, 2026Updated 2 weeks ago
Alternatives and similar repositories for MTPLX
Users that are interested in MTPLX are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar☆23,764Updated this week
- Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with c…☆2,502Updated this week
- A local inference engine for Apple silicon, built around the model.☆2,521Updated this week
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆794Aug 20, 2026Updated 3 months ago
- Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused o…☆4,167Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Sushi engine runs very high quality quant model in Apple Silicon, using both STQ and EXL3 format with special tuning technology to achiev…☆498Updated this week
- Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gem…☆743Nov 8, 2026Updated last week
- MLX Studio - Easiest way to run LLM's on your Mac. All in one engine.☆991Nov 7, 2026Updated 2 weeks ago
- 🔥 The fastest local AI engine for Apple Silicon. Optimised for agentic use.☆99May 24, 2026Updated 5 months ago
- LLM Inference Engine for Metal, CUDA and Vulkan.☆2,354Updated this week
- vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm☆923Nov 7, 2026Updated 2 weeks ago
- MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.☆5,863Updated this week
- Exact speculative decoding on Apple Silicon, powered by MLX.☆390Apr 20, 2026Updated 7 months ago
- Run LLMs with MLX☆7,709Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal mode…☆1,656Nov 7, 2026Updated last week
- DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm☆24,414Nov 8, 2026Updated last week
- ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache…☆802Updated this week
- vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon☆274Jun 3, 2026Updated 5 months ago
- MiniMax H3 inference engine for Mac computers☆3,085Aug 11, 2026Updated 3 months ago
- Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unslot…☆1,475Jun 23, 2026Updated 4 months ago
- JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon☆233Nov 2, 2026Updated 2 weeks ago
- Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.☆1,607Updated this week
- Own your AI. The open-source agent harness for macOS. Run local or cloud models with persistent memory, skills, tools, and autonomous exe…☆8,188Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,254Aug 18, 2026Updated 3 months ago
- A native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.☆290Oct 27, 2026Updated 3 weeks ago
- Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai☆834Updated this week
- Unofficial M1/M2 port of Inco's Splash (upstream is M3+ only): Metal kernels written for Apple7/8 GPUs, prebuilt releases.☆248Updated this week
- Train Large Language Models on MLX.☆473Updated this week
- Apple MLX native implementations of state-of-the-art generative image & video models☆2,630Updated this week
- A high-performance inference engine for AI models☆3,375Updated this week
- A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speec…☆8,308Updated this week
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 7 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Community maintained hardware plugin for vLLM on Apple Silicon☆2,008Updated this week
- Qwen 3.8 27B at 48-65 tok/s on a Mac Studio M4 Max — measured oMLX native-MTP recipe, same-day A/B vs mlx-vlm+MTP sidecar, raw benchmark …☆72Aug 21, 2026Updated 2 months ago
- REAP expert pruning for MoE LLMs on Apple Silicon via MLX☆58Mar 16, 2026Updated 8 months ago
- MLX: An array framework for Apple silicon☆29,223Updated this week
- Qwen 3.8 27B MLX challenge — placeholder, not yet open.☆57Aug 29, 2026Updated 2 months ago
- Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.☆32,711Updated this week
- Fork of antirez/ds4 for Apple Silicon, tuned mostly for M1/M2: Qwen3.8-Flash-Next with 262K context on 64 GB and up, 35 tok/s on an M1 Ma…☆42Updated this week
Are these results useful?