SuperNova-Medius-FP8-Dynamic

This is a FP8-quantized version of arcee-ai/SuperNova-Medius using the llmcompressor library.

For more information about the quantization method, please visit FP8 documentation used for quantization.

Downloads last month
11
Safetensors
Model size
15B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nfunctor/SuperNova-Medius-FP8-Dynamic

Base model

Qwen/Qwen2.5-14B
Quantized
(17)
this model