Hugging Face's logo

AlejandroOlmedo
/
OpenThinker-32B-8bit-mlx

Text Generation
Transformers
Safetensors
MLX
qwen2
llama-factory
full
Generated from Trainer
mlx-my-repo
conversational
text-generation-inference
8-bit precision
Model card Files Community
AlejandroOlmedo commited on
Commit
0e81e1a
·
verified ·
1 Parent(s): 2e29eb8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -29,6 +29,13 @@ model-index:
29
 
30
  I simply converted it to MLX format with a quantization of 8-bit for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips).
31
 
 
 
 
 
 
 
 
32
  # Alejandroolmedo/OpenThinker-32B-8bit-mlx
33
 
34
  The Model [Alejandroolmedo/OpenThinker-32B-8bit-mlx](https://huggingface.co/Alejandroolmedo/OpenThinker-32B-8bit-mlx) was converted to MLX format from [open-thoughts/OpenThinker-32B](https://huggingface.co/open-thoughts/OpenThinker-32B) using mlx-lm version **0.20.5**.
 
29
 
30
  I simply converted it to MLX format with a quantization of 8-bit for better performance on Apple Silicon Macs (M1,M2,M3,M4 Chips).
31
 
32
+ ## Other Types:
33
+ | Link | Type | Size| Notes |
34
+ |-------|-----------|-----------|-----------|
35
+ | [MLX] (https://huggingface.co/Alejandroolmedo/OpenThinker-32B-8bit-mlx) | 8-bit | 34.80 GB | **Best Quality** |
36
+ | [MLX] (https://huggingface.co/Alejandroolmedo/OpenThinker-32B-4bit-mlx) | 4-bit | 18.40 GB | Good Quality|
37
+
38
+
39
  # Alejandroolmedo/OpenThinker-32B-8bit-mlx
40
 
41
  The Model [Alejandroolmedo/OpenThinker-32B-8bit-mlx](https://huggingface.co/Alejandroolmedo/OpenThinker-32B-8bit-mlx) was converted to MLX format from [open-thoughts/OpenThinker-32B](https://huggingface.co/open-thoughts/OpenThinker-32B) using mlx-lm version **0.20.5**.