Local AI tools

The local-first AI stack, in one trackable index

Ollama, LM Studio, Mistral, llama.cpp + every other self-hosted runtime, UI, framework, and open-weight model family we cover. Follow a platform to surface release updates in your feed.

Network status: all quiet — no open community reports across 11 tracked platforms.Full status board →

What can your computer run?Four quick questions, an honest answer for every model size.

Inference runtime

3 platforms

Ollama
One-line local model serving with smart quant manifests
macOS · Linux · Windows· MIT
llama.cpp
The C++ inference engine under most of the local stack
macOS · Linux · Windows · iOS · Android· MIT
vLLM
High-throughput inference server with PagedAttention
Linux + NVIDIA GPU primary; AMD ROCm + CPU also supported· Apache 2.0

Desktop / web UI

6 platforms

Library / framework

1 platform

Apple MLX
Apple Silicon-native ML framework + model library
Apple Silicon only (M1+)· MIT

Model family

1 platform

Mistral
Open-weight model family from Mistral AI
Open weights on Hugging Face· Apache 2.0 (open weights)

The local-first AI stack, in one trackable index

Inference runtime

Ollama

llama.cpp

vLLM

Desktop / web UI

LM Studio

KoboldCPP

Library / framework

Apple MLX

Model family

Mistral

text-generation-webui

GPT4All

Open WebUI

Jan