Downloads · 30 days
31.3K
54% of all-time downloads
Qwen3.8-27B-oQ4e-mtp
Jundot/Qwen3.8-27B-oQ4e-mtp
Qwen3.8-27B-oQ4e-mtp is a image-text-to-text model from Jundot. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
[!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.
All-time downloads
58.2K
Public
Parameters
27.8B
17.5 GB on disk
Likes
84
Trending 6
Repo makeup
Click a slice to open those files.
.safetensors17.5 GB · 100%
Parameter types
How the weights are stored.
U3227.3B · 98%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B-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/Qwen3.8-27B, 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 4.840 bits/weight for the language backbone and 5.044 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 (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 4-bit, group 64 | 19.393B | 69.807% | 10.160 GiB | 4.50 |
| Affine 5-bit, group 64 | 6.579B | 23.680% | 4.212 GiB | 5.50 |
| Affine 6-bit, group 64 | 1.282B | 4.615% | 0.970 GiB | 6.50 |
| Affine 8-bit, group 64 | 0.011B | 0.041% | 0.011 GiB | 8.50 |
| BF16 | 0.516B | 1.857% | 0.961 GiB | 16.00 |
| Total | 27.781B | 100% | 16.314 GiB | 5.044 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language backbone | 26.896B | 16.272 GB / 15.155 GiB |
| Vision encoder | 0.461B | 0.921 GB / 0.858 GiB |
| MTP head | 0.425B | 0.323 GB / 0.301 GiB |
| Total | 27.781B | 17.517 GB / 16.314 GiB |
License
Apache-2.0, following the source model. See LICENSE.
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Aug 17, 2026
- Updated
- Oct 29, 2026