library_name: mlx
tags:
- mlx
- oq
- quantized
- mtp
Qwen3.8-27B-Ultimate-Heretic-Uncensored-oQ2e-mtp
This model was quantized using oQ (oMLX v0.8.0rc1) mixed-precision quantization.
The effective average is 3.406 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 2-bit, group 64 | 12.387B | 44.588% | 3.605 GiB | 2.50 |
| Affine 3-bit, group 128 | 10.453B | 37.627% | 3.955 GiB | 3.25 |
| Affine 3-bit, group 64 | 1.271B | 4.576% | 0.518 GiB | 3.50 |
| Affine 4-bit, group 64 | 0.372B | 1.340% | 0.195 GiB | 4.50 |
| Affine 5-bit, group 64 | 2.781B | 10.012% | 1.781 GiB | 5.50 |
| BF16 | 0.516B | 1.857% | 0.961 GiB | 16.00 |
| Total | 27.781B | 100% | 11.015 GiB | 3.406 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 26.896B | 10.591 GB / 9.864 GiB |
| Vision | 0.461B | 0.921 GB / 0.858 GiB |
| MTP head | 0.425B | 0.314 GB / 0.293 GiB |
| Total | 27.781B | 11.827 GB / 11.015 GiB |