Qwen3.6-35B-A3B oQe MTP
Collection
8 items • Updated
Qwen3.6-35B-A3B-oQ6e-mtp
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 6.746 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 6-bit, group 128 | 0.252B | 0.700% | 0.183 GiB | 6.25 |
| Affine 6-bit, group 64 | 33.018B | 91.838% | 24.984 GiB | 6.50 |
| Affine 8-bit, group 128 | 0.129B | 0.359% | 0.124 GiB | 8.25 |
| Affine 8-bit, group 64 | 2.076B | 5.774% | 2.054 GiB | 8.50 |
| BF16 | 0.478B | 1.329% | 0.890 GiB | 16.00 |
| Total | 35.952B | 100% | 28.235 GiB | 6.746 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 34.661B | 28.720 GB / 26.747 GiB |
| Vision | 0.447B | 0.893 GB / 0.832 GiB |
| MTP head | 0.845B | 0.704 GB / 0.656 GiB |
| Total | 35.952B | 30.317 GB / 28.235 GiB |
- Downloads last month
- 159
Model size
36B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for scottlowry/Qwen3.6-35B-A3B-oQ6e-mtp
Base model
Qwen/Qwen3.6-35B-A3B