Index-Translate-9B-oQ4e-mtp
This model was quantized using oQ (oMLX v0.7.3.dev1) mixed-precision quantization.
The effective average is 5.158 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 | 8.499B | 88.044% | 4.452 GiB | 4.50 |
| Affine 5-bit, group 64 | 0.613B | 6.352% | 0.393 GiB | 5.50 |
| Affine 6-bit, group 64 | 0.050B | 0.521% | 0.038 GiB | 6.50 |
| BF16 | 0.491B | 5.083% | 0.914 GiB | 16.00 |
| Total | 9.653B | 100% | 5.797 GiB | 5.158 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 8.954B | 5.127 GB / 4.775 GiB |
| Vision | 0.456B | 0.912 GB / 0.849 GiB |
| MTP head | 0.243B | 0.185 GB / 0.172 GiB |
| Total | 9.653B | 6.224 GB / 5.797 GiB |
- Downloads last month
- 44
Model size
10B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support