Downloads · 30 days
18
9% of all-time downloads
Qwen3.8-27B-oQ8-mtp
himefei/Qwen3.8-27B-oQ8-mtp
Qwen3.8-27B-oQ8-mtp is a machine learning model from himefei. 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.
This model was quantized using oQ (oMLX v0.6.0.dev1) mixed-precision quantization.
All-time downloads
202
Public
Parameters
27.8B
30 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors30 GB · 100%
Parameter types
How the weights are stored.
U3227.3B · 98%
Model card
From the Hugging Face model README
Qwen3.8-27B-oQ8-mtp
This model was quantized using oQ (oMLX v0.6.0.dev1) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 8
- Group size: 64
- Format: MLX safetensors
Why plain oQ (not oQ+ or oQe)
Official Qwen3.8 support in oMLX is still unmerged (as a draft PR at the time of this quant), so the newer oQe imatrix-calibrated path hasn't been validated for this architecture yet. oQ8 also uses fixed heuristic bit allocation rather than sensitivity/importance-driven allocation, so imatrix calibration wouldn't meaningfully change the result at 8-bit anyway. Plain oQ was the safer choice.
- Library
- mlx
- Type
- qwen3_5
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026