Downloads · 30 days
93
34% of all-time downloads
Qwen3.5-9B-oQ8e-fp16-mtp
scottlowry/Qwen3.5-9B-oQ8e-fp16-mtp
Qwen3.5-9B-oQ8e-fp16-mtp is a machine learning model from scottlowry. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.
[!NOTE] Updated 2026-10-25: Re-quantized with oMLX v0.7.3.dev2. Please re-download if you have an earlier copy.
All-time downloads
274
Public
Parameters
9.7B
34.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors11.6 GB · 100%
Parameter types
How the weights are stored.
U329.2B · 95%
Base models
Model card
From the Hugging Face model README
Qwen3.5-9B-oQ8e-fp16-mtp
[!NOTE] 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 9.637 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 | 9.162B | 94.917% | 9.067 GiB | 8.50 |
| FP16 | 0.035B | 0.359% | 0.065 GiB | 16.00 |
| FP32 | 0.456B | 4.724% | 1.699 GiB | 32.00 |
| Total | 9.653B | 100% | 10.830 GiB | 9.637 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 8.954B | 9.514 GB / 8.861 GiB |
| Vision | 0.456B | 1.824 GB / 1.699 GiB |
| MTP head | 0.243B | 0.290 GB / 0.270 GiB |
| Total | 9.653B | 11.628 GB / 10.830 GiB |
- Library
- mlx
- Type
- qwen3_5
- Created
- Jul 24, 2026
- Updated
- Oct 25, 2026