Cluster 635259

srvsngh99/Krill

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

vllm-project/vllm-metal

Community maintained hardware plugin for vLLM on Apple Silicon

apocryphx/Apertura

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

joshuarossi/mlx-bun

MLX inference for TypeScript/Bun on Apple Silicon. Native library and signed…

carloslfu/slotstream

Run a 105 GB AI model on a 48 GB Mac. Qwen3.8-Flash-Next (125B mixture of experts) streams its…

nanguoyu/minirun-app

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

jundot/omlx

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

nielspeter/mlx-ts

A TypeScript MLX SDK over Apple's mlx-c via FFI. Runs on Bun, Deno and Node; output matches Apple's…

walter-grace/expert-sniper

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

PipeNetwork/inkling-mlx

Run Thinking Machines Lab's Inkling (975B-A41B MoE, multimodal) on Apple Silicon with MLX —…

youssofal/MTPLX

The fastest way to run Qwen 3.8 Flash Next and Qwen 3.8 27B on a Mac: 125 tok/s in OpenCode on an…

jonready/vllm-ios

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

raullenchai/Rapid-MLX

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

szibis/mlx-flash

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

Keith-CY/melix

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

ddalcu/mlx-serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python.…

sethdford/gemma-realtime

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

waybarrios/vllm-mlx

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

Greninja9257/LabLLM

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

Blaizzy/mlx-vlm

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

cryptopoly/ChaosEngineAI

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

dthinkr/mlx-lens

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

ivanfioravanti/vlm-bakeoff

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

jjang-ai/jangq

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime…

Hemeskyo/TimesFM-3-MLX

A pure-MLX port of Google Research's TimesFM-3, a 330M-parameter foundation model for time-series…

sebastien-burel/KaozKit

JavaScript LLM agents on the XS engine, embedded in Swift. Snapshots, resident agents, confined…

yanun0323/Whallm

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash-FP8 inference in ~18…

drumih/turbo-fieldfare

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

mlx-node/mlx-node

No description

argonautlabsai/argodrive

Layout, balancer and instruments for running mixture-of-experts models from SSDs. Three models, two…

NightMean/OlliteRT

Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and…