aws-prototyping/Qwen3-235B-A22B-Thinking-2507_MXFP4

Qwen3-235B-A22B-Thinking-2507_MXFP4

This checkpoint is a variant of Qwen3-235B-A22B-Thinking-2507, where expert weights have been quantized to MXFP4 format similarly to gpt-oss-20b and gpt-oss-120b.

For quantizing weights we used the function downcast_to_mxfp from triton-kernels.

The checkpoint might come with a small drop in accuracy, but has ~71% size reduction compared to the original BF16 checkpoint.

Accuracy Comparison

Checkpoint Size