YHacker Newsscreenshots

oMLX omlx.ai ↗

An MLX-based local LLM inference server for Apple Silicon.

ToolAI & MLapple-siliconlocal-inferencemoe-offloadingmlxlocal-llm

Screenshot of omlx.ai, oMLX's site

Captured 5 Nov 2026

Recommended in 2 threads

Apple has new Mac app coming to make running local AI models easy
9to5mac.com · 3 days ago
Used to run Qwen with a long context window on a 32GB Mac mini.
Kimi K3.1 Pro model weights are out
huggingface.co · 9 days ago
Supports MTP, n-gram table offload and expert offloading to fit big MoE models on Macs.

Similar tools

mlx-vlm ↗AI & ML
A library for running vision-language models on Apple Silicon via MLX.
1 thread
Kapitsa ↗AI & ML
An LLM inference engine for running models locally.
1 thread
LocalCode ↗AI & ML
A Mac app for running large local AI models.
1 thread
exo ↗AI & ML
Software for running AI models across a cluster of local devices.
2 threads
Baseten ↗AI & ML
A model inference hosting platform with a fast serving mode.
0 threads
llama-swap ↗AI & ML
A proxy that swaps between local LLM inference servers on demand.
2 threads
OpenClaw ↗AI & ML
An open personal AI assistant agent platform.
1 thread
TensorFold ↗AI & ML
A project building fast inference engines for Qwen models on Mac and CUDA.
1 thread

Also in AI & ML

OpenRouter ↗
A marketplace that routes API requests to many LLM inference providers.
19 threads
DeepSeek ↗
A family of large language models offered via a low-cost API.
12 threads
llama.cpp ↗
A C/C++ engine for running LLMs locally.
12 threads
GLM ↗
An open-weights large language model family from Zhipu AI.
11 threads
Qwen ↗
Alibaba's family of open-weight large language models.
9 threads
DeepSeek V4.1 Flash ↗
A low-cost DeepSeek language model available via API.
8 threads
Artificial Analysis ↗
A site benchmarking and comparing AI models on quality, price and speed.
7 threads
Claude ↗
Anthropic's AI model and command-line assistant.
7 threads
Qwen 3.8 Flash Next ↗
A Qwen open-weight model that can be run locally.
5 threads
Strata ↗
An open-source project for running large MoE models on small-VRAM GPUs with system RAM.
5 threads
OpenCode Go ↗
A subscription plan for accessing models through the OpenCode coding tool.
4 threads
Pangram ↗
A service that uses a trained model to detect AI-generated text.
4 threads

Link from a commenter, not checked or endorsed by us: ↗ https://omlx.ai/