Qwen3-Reranker-4B-oQ8e
Updated 2026-10-25: Re-quantized with oMLX v0.7.3.dev2. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.7.3.dev2) mixed-precision quantization.
The effective average is 8.500 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 | 4.022B | 99.995% | 3.979 GiB | 8.50 |
| BF16 | 0.000B | 0.005% | 0.000 GiB | 16.00 |
| Total | 4.022B | 100% | 3.980 GiB | 8.500 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 4.022B | 4.273 GB / 3.980 GiB |
| Total | 4.022B | 4.273 GB / 3.980 GiB |
- Downloads last month
- 94
Model size
4B 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