mlx-community/Kimi-K2.5-3bit
This model mlx-community/translategemma-27b-it-bf16 was converted to MLX format from google/translategemma-27b-it using mlx-lm version 0.30.6.
Usage
Please see the model card of the original model for example code.
Note that this model needs to use a very specific translation template.
- Downloads last month
- 170
Model size
27B params
Tensor type
BF16
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for mlx-community/translategemma-27b-it-bf16
Base model
google/translategemma-27b-it