Downloads · 30 days
27
2% of all-time downloads
DeepSeek-V3.1-Terminus-MLX-mixed_4_6
finding1/DeepSeek-V3.1-Terminus-MLX-mixed_4_6
DeepSeek-V3.1-Terminus-MLX-mixed_4_6 is a text generation model from finding1. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as mit.
This model finding1/DeepSeek-V3.1-Terminus-MLX-mixed46 was converted to MLX format from deepseek-ai/DeepSeek-V3.1-Terminus using mlx-lm version 0.28.0 plus pull request 494 with
All-time downloads
1.4K
Public
Parameters
671B
403 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors403 GB · 100%
Parameter types
How the weights are stored.
U32671B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
This model finding1/DeepSeek-V3.1-Terminus-MLX-mixed_4_6 was
converted to MLX format from deepseek-ai/DeepSeek-V3.1-Terminus
using mlx-lm version 0.28.0 plus pull request #494 with
mlx_lm.convert --quantize --q-bits 4 --mlx-path MLX-mixed_4_6 --quant-predicate mixed_4_6 --hf-path deepseek-ai/DeepSeek-V3.1-Terminus.
The console reported 4.809 bits per weight.
- Task
- Text Generation
- Library
- mlx
- Type
- deepseek_v3
- License
- mit
- Created
- Sep 25, 2025
- Updated
- Sep 26, 2025