xDAN-AI
/

APUS-xDAN-4.0-MOE

Inference Endpoints

Model card Files Files and versions Community

xDAN2099 commited on Apr 2

Commit

3629e1f

•

1 Parent(s): b31f896

Update README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -31,12 +31,12 @@ The following specifications:
 - **Maximum Sequence Length (context):** 32,768 tokens
 ## Usage
-| Model       | Quantized | Size   | Hardware Requirement     |
-|-------------|-----------|--------|--------------------------|
-| APUS-xDAN4.0-MoE-0402.Q2_K.gguf       | Q2_K        | 39G  | 2x24G GPU memory |
-| APUS-xDAN4.0-MoE-0402.Q3_K_M_Matrix.gguf      | Q3_K_M        | 51G | 2x24G GPU memory |
-| Large       | No        | Large  | 3x24G GPU memory |
-| APUS-xDAN4.0-MoE-0402.Q4_K_M.gguf | Q4_K_M       | 64G  | 3x24G GPU memory |

 - **Maximum Sequence Length (context):** 32,768 tokens
 ## Usage
+| Model       | Quantized | Size   | Context     | Hardware Requirement     |
+|-------------|-----------|--------|--------------------------| --------------------------|
+| APUS-xDAN4.0-MoE-0402.Q2_K.gguf       | Q2_K        | 39G  | 32k | 2x24G GPU memory |
+| APUS-xDAN4.0-MoE-0402.Q3_K_M_Matrix.gguf      | Q3_K_M        | 51G | 32k | 2x24G GPU memory |
+| Large       | No        | Large  | 32k | 2x24G GPU memory |
+| APUS-xDAN4.0-MoE-0402.Q4_K_M.gguf | Q4_K_M       | 64G  | 32k | 2x24G GPU memory |