neuralmagic
/

pixtral-12b-quantized.w8a8

Image-Text-to-Text

Inference Endpoints

8-bit precision

compressed-tensors

Model card Files Files and versions Community

shubhrapandit commited on 26 days ago

Commit

725500d

·

verified ·

1 Parent(s): 4bac285

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ library_name: transformers
   - **Input:** Vision-Text
   - **Output:** Text
 - **Model Optimizations:**
-  - **Weight quantization:** INT4
   - **Activation quantization:** FP16
 - **Release Date:** 2/24/2025
 - **Version:** 1.0

   - **Input:** Vision-Text
   - **Output:** Text
 - **Model Optimizations:**
+  - **Weight quantization:** INT8
   - **Activation quantization:** FP16
 - **Release Date:** 2/24/2025
 - **Version:** 1.0