Downloads · 30 days
42
19% of all-time downloads
jancirnodziewiaty/Serenity-26B-A4B-oQ4e
Serenity-26B-A4B-oQ4e 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 2026-10-20: Re-quantized with oMLX v0.7.1rc1. Please re-download if you have an earlier copy.
Downloads · 30 days
42
19% of all-time downloads
All-time downloads
225
Public
Parameters
25.8B
15.8 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors15.8 GB · 100%
How the weights are stored.
U3225.2B · 98%
From the Hugging Face model README
[!NOTE] Updated 2026-10-20: Re-quantized with oMLX v0.7.1rc1. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.7.1rc1) mixed-precision quantization.
The effective average is 4.899 bits/weight for the complete checkpoint.
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 4-bit, group 64 | 24.103B | 93.402% | 12.627 GiB | 4.50 |
| Affine 5-bit, group 64 | 0.255B | 0.988% | 0.163 GiB | 5.50 |
| Affine 6-bit, group 64 | 0.053B | 0.205% | 0.040 GiB | 6.50 |
| Affine 8-bit, group 64 | 0.814B | 3.154% | 0.805 GiB | 8.50 |
| BF16 | 0.581B | 2.252% | 1.082 GiB | 16.00 |
| Total | 25.806B | 100% | 14.718 GiB | 4.899 |
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 25.236B | 14.664 GB / 13.657 GiB |
| Vision | 0.570B | 1.139 GB / 1.061 GiB |
| Total | 25.806B | 15.803 GB / 14.718 GiB |