Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.
☆126Jun 13, 2026Updated 2 months ago
Alternatives and similar repositories for mlx-flash
Users that are interested in mlx-flash are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆36Mar 30, 2026Updated 4 months ago
- ☆221Mar 24, 2026Updated 4 months ago
- Running a big model on a small laptop☆4,072Mar 19, 2026Updated 4 months ago
- ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache…☆742Updated this week
- REAP expert pruning for MoE LLMs on Apple Silicon via MLX☆58Mar 16, 2026Updated 5 months ago
- 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.
- PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal ac…☆308Jun 5, 2026Updated 2 months ago
- Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork☆126Updated this week
- Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in MLX☆21Oct 8, 2024Updated last year
- 😼 OpenFelix — Voice-first AI agent for macOS. Runs local LLMs on Apple Silicon via MLX. Supports all OpenClaw skills. Claude, GPT, or fu…☆31Mar 6, 2026Updated 5 months ago
- Provides a frame iterator for videos by using ffmpeg. Decodes images using the image crate.☆12Mar 31, 2021Updated 5 years ago
- ☆86Mar 3, 2026Updated 5 months ago
- MLX Model Quantization Toolkit - Comprehensive collection of Jupyter notebooks for converting and quantizing large language models usi…☆16Aug 16, 2025Updated last year
- ☆21Oct 9, 2024Updated last year
- Shared personal notes created while working with the Apple MLX machine learning framework☆24Dec 12, 2025Updated 8 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- MLX version of DINO DETR☆17Dec 26, 2024Updated last year
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆766Jun 11, 2026Updated 2 months ago
- A repo of useful MLX skills.☆87Jan 25, 2026Updated 6 months ago
- Swift 6 agent SDK: type-safe tools, streaming, cloud + on-device inference via MLX on Apple Silicon☆29Aug 12, 2026Updated last week
- An MLX port of Meta's Coconut reasoning model☆16Sep 2, 2025Updated 11 months ago
- [WIP] Open source implementation of Apple's UXKit PrivateFramework☆28Jun 15, 2026Updated 2 months ago
- A wrapper around Apple's Container framework that looks and feels like docker compose☆17Jun 19, 2025Updated last year
- Este repositorio sirve como guia para la tecnologia vista en el curso. El codigo presente no es absoluto y se puede considerar como plagi…☆15Mar 16, 2026Updated 5 months ago
- Run Time Series Foundation Models on Apple Silicon☆36Feb 27, 2026Updated 5 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Framework for neural network model creating, training and using in predicting written with use of Metal Performance Shaders☆31Nov 5, 2024Updated last year
- ☆67Jun 4, 2026Updated 2 months ago
- My reasearch of losslessly compressing LLM weights.☆64Jul 23, 2026Updated 3 weeks ago
- 6 - m a l w a r e - p a n e l.☆49Mar 18, 2026Updated 5 months ago
- Swift5 ICS Parser, RFC5545 compliant. Nowadays maintained mostly by @superhuman☆11Jun 17, 2020Updated 6 years ago
- macOS audio loopback driver☆16Oct 16, 2020Updated 5 years ago
- Local AI runtime for training & running small LLMs directly on Apple Neural Engine (ANE). No CoreML. No Metal. Offline, on-device fine-tu…☆112Aug 3, 2026Updated 2 weeks ago
- MLX Model Manager unifies loading and inferencing with LLMs and VLMs.☆102Jan 30, 2025Updated last year
- Train and run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely☆158Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Train Large Language Models on MLX.☆407Updated this week
- A Swift library for serializing Codable types to and from [String: Any].☆20Jul 24, 2023Updated 3 years ago
- Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port wi…☆145Apr 15, 2026Updated 4 months ago
- run embeddings in MLX☆98Sep 27, 2024Updated last year
- Run models too big for your Mac's memory☆666Apr 8, 2026Updated 4 months ago
- MacForge/SIMBL plugin for Bartender 3 to expand on mouse hover☆11Oct 4, 2019Updated 6 years ago
- CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.☆131Dec 27, 2024Updated last year