Qwen3.8-27B-oQ6e-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/Qwen3.8-27B, a 27B dense vision-language model built on the Qwen3.5 architecture, with a hybrid layout of Gated DeltaNet and Gated Attention layers, image and video understanding and a 262,144-token native context. It includes the language model, the vision encoder and the multi-token prediction (MTP) head.
The effective average is 6.700 bits/weight for the language backbone and 6.872 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
oQ6e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (128 samples x 512 tokens) and a weighted least-squares refit of its scale and bias.
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 6-bit, group 64 | 24.543B | 88.345% | 18.572 GiB | 6.50 |
| Affine 8-bit, group 64 | 2.722B | 9.798% | 2.694 GiB | 8.50 |
| BF16 | 0.516B | 1.857% | 0.961 GiB | 16.00 |
| Total | 27.781B | 100% | 22.226 GiB | 6.872 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language backbone | 26.896B | 22.526 GB / 20.979 GiB |
| Vision encoder | 0.461B | 0.921 GB / 0.858 GiB |
| MTP head | 0.425B | 0.418 GB / 0.389 GiB |
| Total | 27.781B | 23.865 GB / 22.226 GiB |
License
Apache-2.0, following the source model. See LICENSE.