Repolode
Submit
0xSojalSec

0xSojalSec/LLMs-local

A curated awesome-list of platforms, engines, UIs, models, tools and tutorials for running LLMs locally on your own hardware.

View on GitHub
Stars
1,198
Forks
138
Open issues
12
Last commit
4 months ago

What is it?

LLMs-local is a curated list of resources for running large language models on your own machine rather than through a hosted API. It is organized into sections covering inference platforms and engines, user interfaces, specific open-weight models, agent frameworks, Model Context Protocol servers, retrieval-augmented generation, coding agents, memory layers, evaluation tools, hardware, and tutorials.

Entries link to projects such as Ollama, llama.cpp, vLLM, LM Studio and Open WebUI, with short one-line descriptions of each. The list also points to model providers and benchmark leaderboards, so readers can compare options before choosing a stack.

The repository is a link collection rather than a software package, so it has no code of its own to install or run.

Key features

  • 01Lists local inference engines such as llama.cpp, Ollama, vLLM and MLX-LM with one-line descriptions.
  • 02Groups chat front-ends like Open WebUI, LM Studio-style clients and SillyTavern.
  • 03Covers agent frameworks, MCP servers and RAG tools that work with local models.
  • 04Includes hardware notes and tutorials on prompt, context and inference topics.

Use cases

  • Choosing an inference engine or desktop app for running models on a personal computer.
  • Finding a local chat interface or coding assistant to pair with open-weight models.
  • Exploring which open models and benchmarks are available before setting up a local stack.

Things to know

  • No license is specified, so reuse terms are unclear.

Topics

#llm#local-llm#inference#awesome-list#ai-tools#open-source-models

FAQ

What is LLMs-local?
A curated awesome-list of platforms, engines, UIs, models, tools and tutorials for running LLMs locally on your own hardware. LLMs-local is a curated list of resources for running large language models on your own machine rather than through a hosted API. It is organized into sections covering inference platforms and engines, user interfaces, specific open-weight models, agent frameworks, Model Context Protocol servers, retrieval-augmented generation, coding agents, memory layers, evaluation tools, hardware, and tutorials.
Is LLMs-local free to use? What license does it have?
LLMs-local has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
Is LLMs-local still maintained?
Updated within 6 months. The last commit to LLMs-local was on Jun 10, 2026.
What can I use LLMs-local for?
Choosing an inference engine or desktop app for running models on a personal computer. Finding a local chat interface or coding assistant to pair with open-weight models. Exploring which open models and benchmarks are available before setting up a local stack.
Where can I get LLMs-local?
The source code and installation instructions are on GitHub: https://github.com/0xSojalSec/LLMs-local

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects