Update README.md

README.md

@@ -26,10 +26,11 @@ Preliminary trials show that converting the entire model to pure Int4 (AWQ/GPTQ)
 
 Variant Overview
 
-| Variant     | Characteristics                                                         | File Size | Recommended Scenario                                     |
-|-------------|-------------------------------------------------------------------------|-----------|----------------------------------------------------------|
-| **Compact** | More Int8 layers, higher fidelity                                       | 414 GB    | Ample GPU memory & strict quality needs (e.g., 8 × A100) |
-| **Lite**    | Only the most critical layers upgraded to Int8; size close to pure Int4 | 355 GB    | Resource-constrained, lightweight server deployments     |
+| Variant     | Characteristics                                                                       | File Size | Recommended Scenario                                                                       |
+|-------------|---------------------------------------------------------------------------------------|-----------|--------------------------------------------------------------------------------------------|
+| **Lite**    | Only the most critical layers upgraded to Int8; size close to pure Int4               | 355 GB    | Resource-constrained, lightweight server deployments                                       |
+| **Compact** | More Int8 layers, relatively higher output quality                                    | 414 GB    | VRAM-sufficient deployments focused on answer quality (e.g., 8 × A100)                     |
+| **Medium**  | Compact plus fully-Int8 attention layers; high quality with reduced long-context loss | 445 GB    | VRAM-rich deployments needing both top answer quality and high concurrency (e.g., 8 × H20) |
 
 Choose the variant that best matches your hardware and quality requirements.