## Mixtral-8x7B-Instruct-v0.1-FP8-v3

* Weights and activations are per-tensor quantized to float8_e4m3.
* Quantization with AutoFP8 with updated activation scaling factor names.
* Calibration dataset: Ultrachat-200k
* Samples: 4096
* Sequence length: 8192

## Evaluation

TBA