Update README.md

README.md

@@ -11,14 +11,31 @@ Future modes will also follow the nautic theme.
 - tbd: all OSS models with Apache2.0 and MIT license
 - tbd: add larger models using advanced compression (REAP, M8, ...)
 
+## Challenge: high quality models in 1/2/4/8/.. GB size
+  - Phone 4GB
+  - Home  8GB
+  - Game 16GB
+  - Pro  32GB
+  - Zero 64GB - 71GB
+  - Server 128GB+
+
+| Quality vs. Size | Casual | Premium | Advanced | Frontier | 
+| :--- | :--- | :-: | :--- | :--- | 
+| 64-71 GB | SOTA | SOTA | SOTA | BETA |
+| 32 GB | SOTA | SOTA | SOTA+ | RESEARCH |
+| 16 GB | SOTA | SOTA+ | BETA | - |
+| 8 GB | SOTA | BETA | BETA | - |
+| 4 GB | SOTA | RESEARCH | - | - |
+| 2 GB | RESEARCH | - | - | - |
+| 1 GB | - | - | - | - |
+
+- SOTA: K quants
+- SOTA+: UD quants
+- BETA: REAP + UD
+- RESEARCH: M8 and better
+
 ## ELO (https://lmarena.ai/leaderboard/text)
-- Challenge: Best compressed model in 1/2/4/8 GB size
-    - Phone 4GB
-    - Home  8GB
-    - Game 16GB
-    - Pro  32GB
-    - Zero 64GB - 71GB
-    - Server 128GB+
+
 - Towards Frontier@Phone (within 40 ELO of #1)	non plus ultra
     - qwen3-vl-235b-a22b-instruct 1415 (-37 ELO) 
         - https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507
@@ -58,3 +75,4 @@ Actual bpw are higher for small models and lower for larger models. Similar to J
 | Q2_K | T2UD1 | 60 | 0.8 |
 | Q2_K | M8HQ | 75 | 0.8 |
 | Q2_K | M8LQ | 60 | 0.4 .. 0.6 |
+