Qwen3-30B-A3B-Instruct-2507-mixed-MXFP8-mxfp4experts

Model Details

This is a MXFP8 quantization of Qwen/Qwen3-30B-A3B-Instruct-2507, generated by AutoRound. Please follow the license of the original model.

Quantization Details

Evaluation

Benchmark Score
gsm8k 0.9340
hellaswag 0.6013
mmlu 0.7913
piqa 0.7982

Produced with autoquant-agent — agent-driven quantize + evaluate + self-heal.

Downloads last month
21
Safetensors
Model size
31B params
Tensor type
BF16
·
U8
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lvkaokao/Qwen3-30B-A3B-Instruct-2507-mixed-MXFP8-mxfp4experts

Quantized
(143)
this model