Downloads · 30 days
494
9% of all-time downloads
Qwen3.8-27B-oQ4e-fp16-mtp
scottlowry/Qwen3.8-27B-oQ4e-fp16-mtp
Qwen3.8-27B-oQ4e-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
5.4K
Public
Parameters
27.8B
53.8 GB on disk
Likes
12
Public
Repo makeup
Click a slice to open those files.
.safetensors18 GB · 100%
Parameter types
How the weights are stored.
U3227.3B · 98%
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B-oQ4e-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 5.175 bits/weight for the complete checkpoint.
Quantization and Bit Distribution
| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 4-bit, group 64 | 23.085B | 83.096% | 12.094 GiB | 4.50 |
| Affine 5-bit, group 64 | 2.909B | 10.471% | 1.863 GiB | 5.50 |
| Affine 6-bit, group 64 | 1.271B | 4.576% | 0.962 GiB | 6.50 |
| FP16 | 0.055B | 0.198% | 0.103 GiB | 16.00 |
| FP32 | 0.461B | 1.658% | 1.716 GiB | 32.00 |
| Total | 27.781B | 100% | 16.737 GiB | 5.175 |
Storage Breakdown
| Component | Logical weights | Storage |
|---|---|---|
| Language model | 26.896B | 15.814 GB / 14.728 GiB |
| Vision | 0.461B | 1.843 GB / 1.716 GiB |
| MTP head | 0.425B | 0.314 GB / 0.293 GiB |
| Total | 27.781B | 17.972 GB / 16.737 GiB |
- Library
- mlx
- Type
- qwen3_5
- Created
- Aug 14, 2026
- Updated
- Oct 25, 2026