ov_intent_analysis_sft-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 9.389 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 | 0.752B | 88.149% | 0.744 GiB | 8.50 |
| BF16 | 0.101B | 11.851% | 0.188 GiB | 16.00 |
| Total | 0.853B | 100% | 0.932 GiB | 9.389 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 0.752B | 0.800 GB / 0.745 GiB |
| Vision | 0.101B | 0.201 GB / 0.187 GiB |
| Total | 0.853B | 1.001 GB / 0.932 GiB |
- Downloads last month
- 57
Model size
0.9B 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