mlx-community
/

Ling-1T-mlx-DQ3_K_M

Text Generation

4-bit precision

Model card Files Files and versions

bibproj commited on 27 days ago

Commit

5ddad14

·

verified ·

1 Parent(s): 18aa478

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ This model [mlx-community/Ling-1T-mlx-DQ3_K_M](https://huggingface.co/mlx-commun
 converted to MLX format from [inclusionAI/Ling-1T](https://huggingface.co/inclusionAI/Ling-1T)
 using mlx-lm version **0.28.1**.
-This is created for people using a single Apple Mac Studio M3 Ultra with 512 GB. The 4-bit version of Link 1T does not fit. Using research results, we aim to get 4-bit performance from a slightly smaller and smarter quantization. It should also not be so large that it leaves no memory for a useful context window.
 ```bash
 pip install mlx-lm

 converted to MLX format from [inclusionAI/Ling-1T](https://huggingface.co/inclusionAI/Ling-1T)
 using mlx-lm version **0.28.1**.
+This is created for people using a single Apple Mac Studio M3 Ultra with 512 GB. The 4-bit version of Ling 1T does not fit. Using research results, we aim to get 4-bit performance from a slightly smaller and smarter quantization. It should also not be so large that it leaves no memory for a useful context window.
 ```bash
 pip install mlx-lm