CAT-Translate-1.4b MLX q8
This repository provides MLX quantized weights (q8) converted from the original model.
Original model: cyberagent/CAT-Translate-1.4b
Quantization: MLX q8 (8-bit).
- Downloads last month
- 21
Model size
0.4B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for hotchpotch/CAT-Translate-1.4b-mlx-q8
Base model
sbintuitions/sarashina2.2-1b
Finetuned
cyberagent/CAT-Translate-1.4b