|
|
--- |
|
|
license: gemma |
|
|
base_model: |
|
|
- google/gemma-3-1b-it |
|
|
- unsloth/gemma-3-1b-it |
|
|
- unsloth/gemma-3-1b-it-GGUF |
|
|
--- |
|
|
|
|
|
This is just a reupload of the quantized 4Q K M version of Gemma 3 1b by Google and unsloth. It is used for benchmark purposes on the Jetson Nano and llama.cpp with CUDA support: |
|
|
|
|
|
- [https://github.com/kreier/llama.cpp-jetson](https://github.com/kreier/llama.cpp-jetson) - 🖳 instructions to compile llama.cpp with CUDA support |
|
|
- [https://github.com/kreier/llama.cpp-jetson.nano](https://github.com/kreier/llama.cpp-jetson.nano) - 🚀 precompiled versions that can be installed on the Jetson in minutes |
|
|
- [https://github.com/kreier/jetson](https://github.com/kreier/jetson) a few other insights and results |
