Intel
/

Qwen3-0.6B-FP8-Test-Only

compressed-tensors

Model card Files Files and versions

FP8 static quantized model with compressored tensors. per-tensor weight and per-tensor activation.

Downloads last month: 3

Safetensors

Model size

0.8B params

Tensor type

BF16

·

F8_E4M3

·

Inference Providers NEW

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