library_name: mlx
tags:
- mlx
- oq
- quantized
- mtp
DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-oQ6h-mtp
[!NOTE]
Updated 2026-11-19: Re-quantized with oMLX v0.8.0. Please re-download if you have an earlier copy.
This model was quantized using oQ (oMLX v0.8.0) mixed-precision quantization.
The effective average is 16.288 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 64 | 2.223B | 52.301% | 1.682 GiB | 6.50 |
| Affine 8-bit, group 64 | 0.021B | 0.493% | 0.021 GiB | 8.50 |
| BF16 | 0.600B | 14.117% | 1.118 GiB | 16.00 |
| U32 | 1.406B | 33.088% | 5.239 GiB | 32.00 |
| Total | 4.250B | 100% | 8.060 GiB | 16.288 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 3.551B | 7.499 GB / 6.984 GiB |
| Vision | 0.456B | 0.912 GB / 0.849 GiB |
| MTP head | 0.243B | 0.243 GB / 0.226 GiB |
| Total | 4.250B | 8.654 GB / 8.060 GiB |