embeddinggemma-2-oQ4e-fp16
This model was quantized using oQ (oMLX v0.7.1.dev1) mixed-precision quantization.
The effective average is 22.140 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 | 0.211B | 28.314% | 0.110 GiB | 4.50 |
| Affine 5-bit, group 64 | 0.033B | 4.367% | 0.021 GiB | 5.50 |
| Affine 6-bit, group 64 | 0.002B | 0.211% | 0.001 GiB | 6.50 |
| Affine 8-bit, group 64 | 0.027B | 3.663% | 0.027 GiB | 8.50 |
| FP16 | 0.000B | 0.010% | 0.000 GiB | 16.00 |
| FP32 | 0.472B | 63.435% | 1.759 GiB | 32.00 |
| Total | 0.744B | 100% | 1.919 GiB | 22.140 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 0.272B | 0.171 GB / 0.160 GiB |
| Vision | 0.167B | 0.669 GB / 0.623 GiB |
| Audio | 0.305B | 1.219 GB / 1.136 GiB |
| Total | 0.744B | 2.060 GB / 1.919 GiB |
- Downloads last month
- 54
Model size
0.7B params
Tensor type
F32
路
U32 路
F16 路
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support
Model tree for zviratko/embeddinggemma-2-oQ4e-fp16
Base model
google/embeddinggemma-2