Qwen3.8-Flash-Next-oQ4e-mtp

Qwen3.8-Flash-Next-oQ4e-mtp

[!NOTE] Updated 2026-10-29: Re-quantized with the improved oQe quantization in oMLX 0.7.3. Please re-download if you have an earlier copy.

This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization with improved oQe (jundot/omlx#4930).

A mixed-precision MLX checkpoint of Qwen/Qwen3.8-Flash-Next, an experimental preview of the architecture behind Qwen4: a mixture-of-experts vision-language model with 125B parameters and 6B activated, plus a 51B n-gram embedding and a 4B MTP module, that pairs Gated DeltaNet with Qwen Sparse Attention (QSA) and uses Gated Residual streams. It includes the language model, the n-gram embedding, the vision encoder and the multi-token prediction (MTP) head.

The effective average is 4.661 bits/weight for the language backbone and 4.785 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

oQ4e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (1024 samples x 512 tokens) and a weighted least-squares refit of its scale and bias.

Storage Breakdown

License

Qwen Community License 1.0, following the source model. See LICENSE.