Downloads · 30 days
110
45% of all-time downloads
Qwen3.5-4B-oQ4e-mtp
scottlowry/Qwen3.5-4B-oQ4e-mtp
Qwen3.5-4B-oQ4e-mtp is a machine learning model from scottlowry. 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 2026-10-25: Re-quantized with oMLX v0.7.3.dev2. Please re-download if you have an earlier copy.
All-time downloads
242
Public
Parameters
4.7B
9.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.3 GB · 99%
Parameter types
How the weights are stored.
U324.3B · 93%
Base models
Model card
From the Hugging Face model README
Qwen3.5-4B-oQ4e-mtp
[!NOTE] Updated 2026-10-25: Re-quantized with oMLX v0.7.3.dev2. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.7.3.dev2) mixed-precision quantization.
The effective average is 5.606 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 | 3.206B | 68.794% | 1.679 GiB | 4.50 |
| Affine 5-bit, group 64 | 1.057B | 22.678% | 0.677 GiB | 5.50 |
| Affine 6-bit, group 64 | 0.050B | 1.069% | 0.038 GiB | 6.50 |
| BF16 | 0.348B | 7.459% | 0.647 GiB | 16.00 |
| Total | 4.660B | 100% | 3.041 GiB | 5.606 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 4.206B | 2.512 GB / 2.339 GiB |
| Vision | 0.334B | 0.667 GB / 0.621 GiB |
| MTP head | 0.121B | 0.087 GB / 0.081 GiB |
| Total | 4.660B | 3.265 GB / 3.041 GiB |
- Library
- mlx
- Type
- qwen3_5
- Created
- Jul 24, 2026
- Updated
- Oct 25, 2026