Submit k8s config w/ Qwen3-Next-80B-A3B-Thinking benchmark

ekur12 · ekur12 · commit 8fa4db9b506b · 2026-03-31T11:21:21.000-04:00
diff --git a/k8s_scenario.toml b/k8s_scenario.toml
@@ -8,7 +8,7 @@ name = "k8s_operator"
 env = {
     OPENAI_API_KEY = "${NEBIUS_API_KEY}",
     OPENAI_API_BASE = "https://api.tokenfactory.nebius.com/v1/",
-    MODEL_NAME = "openai/nvidia/nemotron-3-super-120b-a12b"
+    MODEL_NAME = "openai/Qwen/Qwen3-Next-80B-A3B-Thinking"
 }
 
 [config]

Original file line number	Diff line number	Diff line change
`@@ -8,7 +8,7 @@ name = "k8s_operator"`
`8`	`8`	`env = {`
`9`	`9`	`OPENAI_API_KEY = "${NEBIUS_API_KEY}",`
`10`	`10`	`OPENAI_API_BASE = "https://api.tokenfactory.nebius.com/v1/",`
`11`		`- MODEL_NAME = "openai/nvidia/nemotron-3-super-120b-a12b"`
	`11`	`+ MODEL_NAME = "openai/Qwen/Qwen3-Next-80B-A3B-Thinking"`
`12`	`12`	`}`
`13`	`13`
`14`	`14`	`[config]`