SuperNova g6e.2xlarge

results_arcee_supernova.py

@@ -36,6 +36,14 @@ results_arcee_supernova = {
             "tokensPerSecond": "18",
             "notes": "--max-model-len 10000 --max-num-seqs 16 --enforce-eager",
         },
+        {
+            "instanceType": "g6e.2xlarge",
+            "quantization": "Q4_K_M",
+            "container": "llama.cpp 10/2/24",
+            "status": "OK",
+            "tokensPerSecond": "16",
+            "notes": "-ngl 81 -c 13000 -fa -t 8",
+        },
         {
             "instanceType": "p4d.24xlarge",
             "quantization": "awq",