LFM2.5-2.6B-oQ8e
This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization.
The effective average is 8.501 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 | 2.697B | 99.990% | 2.669 GiB | 8.50 |
| BF16 | 0.000B | 0.010% | 0.000 GiB | 16.00 |
| Total | 2.697B | 100% | 2.669 GiB | 8.501 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 2.697B | 2.866 GB / 2.669 GiB |
| Total | 2.697B | 2.866 GB / 2.669 GiB |
- Downloads last month
- 56
Model size
3B 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