wolfram
/

Mistral-Large-Instruct-2411-2.75bpw-h6-exl2

Model card Files Files and versions Community

wolfram commited on 5 days ago

Commit

467ee59

•

1 Parent(s): 6cb6bb3

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -120,6 +120,8 @@ extra_gated_description: >-
 extra_gated_button_content: Submit
 library_name: vllm
 ---
 # Model Card for Mistral-Large-Instruct-2411

 extra_gated_button_content: Submit
 library_name: vllm
 ---
+> [!NOTE]
+> EXL2 2.75bpw-h6 quantized version of [mistralai/Mistral-Large-Instruct-2411](https://huggingface.co/mistralai/Mistral-Large-Instruct-2411). Supports 32K context with Q4 cache on systems with 48 GB VRAM.
 # Model Card for Mistral-Large-Instruct-2411