Qwen3-1.7B ONNX INT4
This is an ONNX INT4 quantized version of Qwen3-1.7B by Alibaba Cloud, converted for use with onnxruntime-genai.
Model Details
- Base model: Qwen/Qwen3-1.7B
- Format: ONNX
- Quantization: INT4
- License: Apache 2.0
Credits
Original model by Alibaba Cloud / Qwen Team.
ONNX conversion by usmichael.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support