library_name: mlx
tags:
- mlx
- oq
- quantized
- mtp
Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-oQ2.5e-mtp
This model was quantized using oQ (oMLX v0.7.4.dev1) mixed-precision quantization.
The effective average is 3.678 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 | 2.333B | 8.398% | 0.679 GiB | 2.50 |
| Affine 3-bit, group 128 | 20.502B | 73.796% | 7.757 GiB | 3.25 |
| Affine 3-bit, group 64 | 1.271B | 4.576% | 0.518 GiB | 3.50 |
| Affine 4-bit, group 64 | 0.378B | 1.360% | 0.198 GiB | 4.50 |
| Affine 5-bit, group 64 | 2.781B | 10.012% | 1.781 GiB | 5.50 |
| Affine 6-bit, group 64 | 0.000B | 0.001% | 0.000 GiB | 6.50 |
| Affine 8-bit, group 64 | 0.000B | 0.001% | 0.000 GiB | 8.50 |
| BF16 | 0.516B | 1.857% | 0.961 GiB | 16.00 |
| Total | 27.781B | 100% | 11.894 GiB | 3.678 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 26.896B | 11.535 GB / 10.743 GiB |
| Vision | 0.461B | 0.921 GB / 0.858 GiB |
| MTP head | 0.425B | 0.314 GB / 0.293 GiB |
| Total | 27.781B | 12.771 GB / 11.894 GiB |