https://github.com/lrusso/llamaloader
Llama Loader in GGUF format for Web browsers
https://github.com/lrusso/llamaloader
ai browsers gguf javascript llama models web webassembly
Last synced: 7 months ago
JSON representation
Llama Loader in GGUF format for Web browsers
- Host: GitHub
- URL: https://github.com/lrusso/llamaloader
- Owner: lrusso
- Created: 2025-03-10T05:07:12.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-03-10T05:10:33.000Z (7 months ago)
- Last Synced: 2025-03-10T05:23:59.737Z (7 months ago)
- Topics: ai, browsers, gguf, javascript, llama, models, web, webassembly
- Language: HTML
- Homepage:
- Size: 0 Bytes
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Llama Loader
Designed in JavaScript and WebAssembly. With this project you can load and run your model (in GGUF format) on your Web browser. Just select the GGUF file from your computer.
## Web:
https://lrusso.github.io/LlamaLoader/Llama.htm
## Suggested model - Llama 3.2:
* Lightweight model file (732 MB).
* The model has 1.23 billion parameters.
* Supports English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.
* It can be downloaded from [here](https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q3_K_L.gguf?download=true) and others models are available [here](https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF).
## Based on the work of:
https://github.com/ngxson/wllama