Downloads · 30 days
23
1% of all-time downloads
DeepSeek-V3.1-Terminus-MLX-mixed_4_6-v0.28.2
finding1/DeepSeek-V3.1-Terminus-MLX-mixed_4_6-v0.28.2
DeepSeek-V3.1-Terminus-MLX-mixed_4_6-v0.28.2 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-v0.28.2 was converted to MLX format from deepseek-ai/DeepSeek-V3.1-Terminus using mlx-lm version 0.28.2 mlxlm.convert --quantize --q-bits 4 --quant-predicate mixe…
All-time downloads
2K
Public
Parameters
671B
404 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors404 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-v0.28.2 was
converted to MLX format from deepseek-ai/DeepSeek-V3.1-Terminus
using mlx-lm version 0.28.2 mlx_lm.convert --quantize --q-bits 4 --quant-predicate mixed_4_6 --hf-path deepseek-ai/DeepSeek-V3.1-Terminus --mlx-path DeepSeek-V3.1-Terminus-MLX-mixed_4_6-v2. The console reported 4.811 bits per weight. The difference between this and finding1/DeepSeek-V3.1-Terminus-MLX-mixed_4_6 is using 6 bits instead of 4 bits for some self-attention tensors.
- Task
- Text Generation
- Library
- mlx
- Type
- deepseek_v3
- License
- mit
- Created
- Oct 3, 2025
- Updated
- Oct 3, 2025