FreeAIRepo
LLMs & chat

OpenGVLab/OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

MITPython
Stars
964
Forks
93
Open issues
31
Last push
11mo ago

About OmniQuant

OmniQuant is a free, open-source LLM chat app by OpenGVLab, written mainly in Python. [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs. It has 964 GitHub stars and 93 forks, and was last updated 11mo ago. It's released under the MIT license, a standard open-source license.

License
MIT
Language
Python
Stars
964
Last update
11mo ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not stated
Self-hostable
Yes

Similar free tools

All LLMs & chat tools →

OmniQuant FAQ

Is OmniQuant free?

Yes. OmniQuant is open source and free to use. It's released under the MIT license, a standard open-source license.

Does OmniQuant run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does OmniQuant need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is OmniQuant still maintained?

It was last updated 11mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to OmniQuant?

Similar free, open-source tools include Hands-On-Large-Language-Models, Qwen, gpt_academic, FinGPT.

Related topics