KaLM-Embedding/KaLM-embedding-finetuning-data
Viewer • Updated • 6.34M • 713 • 26
How to use thedarkstar/KaLM-Embedding-Gemma3-12B-2511-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir KaLM-Embedding-Gemma3-12B-2511-mlx-4Bit thedarkstar/KaLM-Embedding-Gemma3-12B-2511-mlx-4Bit
The Model thedarkstar/KaLM-Embedding-Gemma3-12B-2511-mlx-4Bit was converted to MLX format from tencent/KaLM-Embedding-Gemma3-12B-2511 using mlx-lm version 0.29.1.
4-bit
Base model
google/gemma-3-12b-pt