matt-k-wong/mlx-flash
Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.
- Stars
- 139
- Forks
- 11
- Open issues
- 0
- Last push
- 4mo ago
mlx-flash star history
+1 this week
About mlx-flash
mlx-flash is a free, open-source LLM chat app by matt-k-wong, written mainly in Python. Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon. It has 139 GitHub stars and 11 forks, and was last updated 4mo ago. It's released under the MIT license, a standard open-source license. According to the project, it works on macOS.
- License
- MIT
- Commercial use
- Commercial OK
- Language
- Python
- Stars
- 139
- Last update
- 4mo ago
- Runs on Mac
- Yes (as stated by the project)
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Yes
Similar free tools
Hands-On-Large-Language-Models30k stars · Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
heretic37k stars · Automatically removes censorship from language models.
FinGPT21k stars · FinGPT is an open-source financial large language model for financial analysis and forecasting.
FastChat40k stars · Train, serve, and evaluate large language models for chatbots.
RWKV-LM15k stars · RWKV-7 is a linear-time RNN language model for large-scale inference and chat applications.
web-llm19k stars · Runs language models in web browsers for AI chatbots and assistants.
mlx-flash FAQ
Can I use mlx-flash commercially?
Yes. MIT is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.
Is mlx-flash free?
Yes. mlx-flash is open source and free to use. It's released under the MIT license, a standard open-source license.
Does mlx-flash run on a Mac?
Yes. According to the project, mlx-flash works on macOS.
Does mlx-flash need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is mlx-flash still maintained?
It was last updated 4mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to mlx-flash?
Similar free, open-source tools include Hands-On-Large-Language-Models, heretic, FinGPT, FastChat.
Maintain mlx-flash?
Add this badge to your README to show it's featured on FreeAIRepo.
[](https://www.freeairepo.com/repo/matt-k-wong/mlx-flash)