Qwen3.8-Flash-Next-NVFP4 (mirror)

This is a mirror, not a quantization by Mia-AiLab.

Weights and files are copied from local-inference-lab/Qwen3.8-Flash-Next-NVFP4. Use that repo as the source of truth.

I did not produce this NVFP4 / ModelOpt quant. Credit and issues belong with the original authors.

Original README:

Work in progress. Details and instructions to follow.

Safetensors

Model size

93B params

Tensor type

BF16

F8_E4M3

I64

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Mia-AiLab/Qwen3.8-Flash-Next-NVFP4

Base model

Quantized

(175)

this model