Hugging Face's logo

fabriziosalmi
/
mini-coder-1.7b-mlx-4bit

MLX
Safetensors
qwen3
quantized
4-bit precision
code-generation
Model card Files
xet
 Community
fabriziosalmi commited on
Commit
32c1f7e
·
verified ·
1 Parent(s): 0330d66

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -14,7 +14,7 @@ This is the [ricdomolm/mini-coder-1.7b](https://huggingface.co/ricdomolm/mini-co
14
 
15
  The conversion was performed to ensure the best trade-off between inference speed and the quality of the generated code, while keeping the unified RAM footprint to a minimum. I got 86 tps on MacBook Pro M4 16GB by using this model in LMStudio.
16
 
17
- ## 💻 How to use it with MLX
18
 
19
  You can load and run this model directly in Python using the official `mlx-lm` library.
20
 
@@ -57,7 +57,7 @@ response = generate(
57
 
58
  ```
59
 
60
- ## ⚙️ Quantization Details
61
 
62
  * **Framework:** MLX
63
  * **Bits:** 4
 
14
 
15
  The conversion was performed to ensure the best trade-off between inference speed and the quality of the generated code, while keeping the unified RAM footprint to a minimum. I got 86 tps on MacBook Pro M4 16GB by using this model in LMStudio.
16
 
17
+ ## How to use it with MLX
18
 
19
  You can load and run this model directly in Python using the official `mlx-lm` library.
20
 
 
57
 
58
  ```
59
 
60
+ ## Quantization Details
61
 
62
  * **Framework:** MLX
63
  * **Bits:** 4