Downloads · 30 days
182
51% of all-time downloads
jancirnodziewiaty/gemma-4-31B-it-scotoma-2-oQ4e-mtp
gemma-4-31B-it-scotoma-2-oQ4e-mtp is a machine learning model from jancirnodziewiaty. 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 2026-11-01: Re-quantized with oMLX v0.7.3. Please re-download if you have an earlier copy.
Downloads · 30 days
182
51% of all-time downloads
All-time downloads
356
Public
Parameters
31.7B
20.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors20.5 GB · 100%
How the weights are stored.
U3230.7B · 97%
From the Hugging Face model README
[!NOTE] Updated 2026-11-01: Re-quantized with oMLX v0.7.3. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization.
The effective average is 5.167 bits/weight for the complete checkpoint.
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 4-bit, group 64 | 21.878B | 68.922% | 11.461 GiB | 4.50 |
| Affine 5-bit, group 64 | 8.445B | 26.604% | 5.407 GiB | 5.50 |
| Affine 6-bit, group 64 | 0.380B | 1.197% | 0.287 GiB | 6.50 |
| BF16 | 1.040B | 3.278% | 1.938 GiB | 16.00 |
| Total | 31.743B | 100% | 19.093 GiB | 5.167 |
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 30.704B | 18.423 GB / 17.158 GiB |
| Vision | 0.570B | 1.139 GB / 1.061 GiB |
| MTP head | 0.470B | 0.939 GB / 0.875 GiB |
| Total | 31.743B | 20.501 GB / 19.093 GiB |