CAT-Translate-7b-oQ5e
Updated 2026-11-03: Re-quantized with oMLX v0.7.3. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization.
The effective average is 5.700 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 5-bit, group 64 | 6.514B | 87.018% | 4.171 GiB | 5.50 |
| Affine 6-bit, group 64 | 0.710B | 9.487% | 0.537 GiB | 6.50 |
| Affine 8-bit, group 64 | 0.261B | 3.492% | 0.259 GiB | 8.50 |
| BF16 | 0.000B | 0.004% | 0.000 GiB | 16.00 |
| Total | 7.486B | 100% | 4.967 GiB | 5.700 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 7.486B | 5.333 GB / 4.967 GiB |
| Total | 7.486B | 5.333 GB / 4.967 GiB |
- Downloads last month
- 17
Model size
7B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
5-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support