π₯ The fastest local AI engine for Apple Silicon. Optimised for agentic use.
β99May 24, 2026Updated 5 months ago
Alternatives and similar repositories for lightning-mlx
Users that are interested in lightning-mlx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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 27Bβ¦β2,727Nov 7, 2026Updated last week
- Real speed. Multi-model LLM serving with prefix reuse, MTP acceleration β built for Apple Siliconβ34Updated this week
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acceβ¦β62Apr 18, 2026Updated 7 months ago
- Run large Mixture-of-Experts language models well on the memory you have.β21Oct 24, 2026Updated 3 weeks ago
- High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal modeβ¦β1,656Nov 7, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial Offer β’ AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- llama.cpp fork for running Qwen3.8-Flash-Next V3 (95.5 GiB) on a 64 GB Apple Silicon Mac by streaming MoE experts from SSD. Setup guide: β¦β13Sep 19, 2026Updated 2 months ago
- β22Oct 18, 2026Updated last month
- More than a writing assistant β BojuBot turns your Obsidian vault into a personal AI platformβ27Updated this week
- Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with cβ¦β2,502Updated this week
- The open-source security layer for AI agents. Deterministic guardrails, PII redaction, and EU AI Act compliance in one line of code.β25May 12, 2026Updated 6 months ago
- A native Mac App for LLM fine-tuning on Apple Silicon β fully on-device, fully open source.β290Oct 27, 2026Updated 3 weeks ago
- Lossless DFlash speculative decoding for MLX on Apple Siliconβ794Aug 20, 2026Updated 3 months ago
- MCP server for any Python command line applicationβ22Aug 1, 2026Updated 3 months ago
- Utilities to evaluate MLX quantizationsβ26Jun 9, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer β’ AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Moshi-Finetune-MLX lets you fine-tune Moshi (Native, Real-Time, Speech-to-Speech) models all on Apple Silicon.β26Apr 21, 2026Updated 6 months ago
- REAP expert pruning for MoE LLMs on Apple Silicon via MLXβ58Mar 16, 2026Updated 8 months ago
- Precision-aware retrieval benchmark for LLM memory systems.β19Sep 17, 2026Updated 2 months ago
- H3MLX: MiniMax-H3 Metal 4 / Pure C Video Gen Master Suite, Benchmark Matrix & AI Agent Skill for Apple Siliconβ25Sep 6, 2026Updated 2 months ago
- A wannabe Ollama equivalent for Apple MlX modelsβ85Mar 2, 2025Updated last year
- LLM inference server with continuous batching & SSD caching for Apple Silicon β managed from the macOS menu barβ23,764Updated this week
- JANG β GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Siliconβ233Nov 2, 2026Updated 2 weeks ago
- Vitruvius is an engineering research agent.β12Nov 8, 2026Updated last week
- Run compiled CoreML(v1) model using MPSNNβ12Dec 27, 2018Updated 7 years ago
- 1-Click AI Models by DigitalOcean Gradient β’ AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Uses conversation history to audit important decisions and changes.β17Jul 13, 2025Updated last year
- π LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual bβ¦β107Oct 15, 2026Updated last month
- Local browser agent: MLX + Chrome DevTools Protocol. Handles cross-origin iframes, Shadow DOM, ProseMirror. Runs on Apple Silicon, no cloβ¦β30Updated this week
- An interactive command-line interface that uses the Agent2Agent (A2A) & Model Context Protocols (MCP) to manage multi-agent systems.β13Jan 1, 2026Updated 10 months ago
- DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCmβ17Oct 22, 2026Updated 3 weeks ago
- Collaborative AI Agent Swarms for Autonomous Task Synchronizationβ17Jun 19, 2025Updated last year
- κ΅κ°μ°κ΅¬κ°λ°(μ λΆ R&D) κ·μ κ²ν μ© MCP μλ² β νμ λ²Β·μνλ ΉΒ·νμ κ·μΉ 55μ’ μ AIλ‘ κ²μΒ·κ²ν (Korean national R&D regulations MCP)β14Nov 12, 2026Updated last week
- A concept tool for displaying video at any aspect ratio. The video frame adapts to the size and orientation of the device, filling the scβ¦β15Jul 21, 2014Updated 12 years ago
- β11Jan 7, 2023Updated 3 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI β’ AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Native macOS music + audiobook + podcast player with a Stremio-style addon system. Self-hosted, single-user, multi-device.β13May 19, 2026Updated 6 months ago
- A local inference engine for Apple silicon, built around the model.β2,521Updated this week
- vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlmβ923Nov 7, 2026Updated last week
- A personal AI agent that can work safely on your machine, remember useful context, and keep its data under your control.β109Aug 31, 2026Updated 2 months ago
- Up to 4Γ faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding β Gemβ¦β743Nov 8, 2026Updated last week
- MiniMax H3 (video + audio) on TensorFold 0.6.5 with an H3 family, Mac Studio M5 Ultra: 5 s 864x480 clip in ~50 s, 40 s at 768x448 β the fβ¦β31Oct 7, 2026Updated last month
- Real-time vLLM + TensorFold performance dashboard TUI β single file, zero dependenciesβ13Oct 19, 2026Updated last month
Are these results useful?