d1-2B-MLX-oQ8e
This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization.
The effective average is 9.242 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 8-bit, group 64 | 1.728B | 90.107% | 1.710 GiB | 8.50 |
| BF16 | 0.190B | 9.893% | 0.353 GiB | 16.00 |
| Total | 1.918B | 100% | 2.064 GiB | 9.242 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 1.729B | 1.837 GB / 1.711 GiB |
| Vision | 0.189B | 0.379 GB / 0.353 GiB |
| Total | 1.918B | 2.216 GB / 2.064 GiB |
- Downloads last month
- 31
Model size
2B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support