Ornith-1.5-35B-A3B oQe MTP
Collection
8 items • Updated • 2
Ornith-1.5-35B-A3B-oQ8e-fp16-mtp
Updated 2026-11-11: Re-quantized with oMLX v0.7.4.dev1. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.7.4.dev1) mixed-precision quantization.
The effective average is 8.789 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 128 | 1.340B | 3.727% | 1.287 GiB | 8.25 |
| Affine 8-bit, group 64 | 34.134B | 94.945% | 33.777 GiB | 8.50 |
| FP16 | 0.031B | 0.086% | 0.058 GiB | 16.00 |
| FP32 | 0.447B | 1.242% | 1.664 GiB | 32.00 |
| Total | 35.952B | 100% | 36.785 GiB | 8.789 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 34.661B | 36.806 GB / 34.279 GiB |
| Vision | 0.447B | 1.786 GB / 1.664 GiB |
| MTP head | 0.845B | 0.905 GB / 0.843 GiB |
| Total | 35.952B | 39.498 GB / 36.785 GiB |
- Downloads last month
- 311
Model size
36B params
Tensor type
U32
·
F16 ·
F32 ·
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
Model tree for scottlowry/Ornith-1.5-35B-A3B-oQ8e-fp16-mtp
Base model
ornith-ai/Ornith-1.5-35B-A3B