bitsandbytes quant of mistralai/Mistral-Large-Instruct-2411

Fits in 80gb vram with unsloth at 8192 context.

Downloads last month
-
Safetensors
Model size
126B params
Tensor type
F32
BF16
U8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support