Downloads · 30 days
23
8% of all-time downloads
Qwen3.8-27B-oQ3e-fp16-mtp
guutong/Qwen3.8-27B-oQ3e-fp16-mtp
Qwen3.8-27B-oQ3e-fp16-mtp is a machine learning model from guutong. 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.
[!IMPORTANT] This quantization was uploaded on 2026-08-23 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
All-time downloads
295
Public
Parameters
27.3B
13 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13 GB · 100%
Parameter types
How the weights are stored.
U3227.3B · 100%
Model card
From the Hugging Face model README
[!IMPORTANT] This quantization was uploaded on 2026-08-23 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.
Qwen3.8-27B-oQ3e-fp16-mtp
This model was quantized using oQ (oMLX v0.6.3rc2) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 3
- Group size: 64
- Format: MLX safetensors
Chat Template
This model now uses the updated chat template from peculiar-ragdoll/Qwen-Sharp-Chat-Templates (v22.4).
- Library
- mlx
- Type
- qwen3_5
- Created
- Aug 23, 2026
- Updated
- Aug 30, 2026