Rin247/Qwen3-ASR-1.7B-hf-FP4

Qwen3 ASR 1.7B hf FP4

FP4 weight-only safetensors quantization of Qwen3-ASR-1.7B-hf.

Quantization Details

• Base model: Qwen3-ASR-1.7B-hf
• Format: FP4 (weight-only safetensors)
• Method: PyTorch RTN quantization on CPU; scales stored alongside weights
• Files: model.safetensors + config.json (contains quantization_config)

Loading

These use custom weight-only recipes. Dequantize with the matching scale/shape buffers (*.weight_scale, *.weight_shape) before feeding to an inference engine.