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.

Safetensors

Model size

14.8B params

Tensor type

BF16

F8_E4M3

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

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

Base model

Qwen/Qwen2.5-14B

Finetuned

Quantized

(17)

this model