Downloads · 30 days
118
33% of all-time downloads
Qwen3.8-27B-oQ4e-mtp
bambocher/Qwen3.8-27B-oQ4e-mtp
Qwen3.8-27B-oQ4e-mtp is a machine learning model from bambocher. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.
[!NOTE] Updated 2026-10-20: Re-quantized with oMLX v0.7.1. Please re-download if you have an earlier copy.
All-time downloads
355
Public
Parameters
27.8B
34 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors17 GB · 100%
Parameter types
How the weights are stored.
U3227.3B · 98%
Model card
From the Hugging Face model README
Qwen3.8-27B-oQ4e-mtp
[!NOTE] Updated 2026-10-20: Re-quantized with oMLX v0.7.1. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization.
The effective average is 4.887 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 4-bit, group 64 | 22.443B | 80.783% | 11.757 GiB | 4.50 |
| Affine 5-bit, group 64 | 4.823B | 17.360% | 3.088 GiB | 5.50 |
| BF16 | 0.516B | 1.857% | 0.961 GiB | 16.00 |
| Total | 27.781B | 100% | 15.806 GiB | 4.887 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 26.896B | 15.736 GB / 14.655 GiB |
| Vision | 0.461B | 0.921 GB / 0.858 GiB |
| MTP head | 0.425B | 0.314 GB / 0.293 GiB |
| Total | 27.781B | 16.971 GB / 15.806 GiB |
- Library
- mlx
- Type
- qwen3_5
- Created
- Aug 18, 2026
- Updated
- Oct 20, 2026