flint-oQ2e
This model was quantized using oQ (oMLX v0.7.3.dev2) mixed-precision quantization.
The effective average is 2.795 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 | 37.849B | 95.134% | 11.016 GiB | 2.50 |
| Affine 8-bit, group 128 | 0.296B | 0.743% | 0.284 GiB | 8.25 |
| Affine 8-bit, group 64 | 1.615B | 4.060% | 1.598 GiB | 8.50 |
| BF16 | 0.025B | 0.063% | 0.046 GiB | 16.00 |
| Total | 39.785B | 100% | 12.944 GiB | 2.795 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 39.785B | 13.899 GB / 12.944 GiB |
| Total | 39.785B | 13.899 GB / 12.944 GiB |
- Downloads last month
- 30
Model size
40B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
2-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for g-oQ/flint-oQ2e
Base model
RecursiveSI/flint