diff --git a/server/sched.go b/server/sched.go
index fcc3a61df..c12e8c0fb 100644
--- a/server/sched.go
+++ b/server/sched.go
@@ -510,7 +510,7 @@ func (s *Scheduler) load(req *LlmRequest, systemInfo ml.SystemInfo, gpus []ml.De
 
 	// Some architectures are not safe with num_parallel > 1.
 	// ref: https://github.com/ollama/ollama/issues/4165
-	if slices.Contains([]string{"mllama", "qwen3vl", "qwen3vlmoe", "qwen35", "qwen35moe", "qwen3next", "lfm2", "lfm2moe", "nemotron_h", "nemotron_h_moe", "nemotron_h_omni"}, req.model.Config.ModelFamily) && numParallel != 1 {
+	if slices.Contains([]string{"mllama", "qwen3vl", "qwen3vlmoe", "qwen3next", "lfm2", "lfm2moe", "nemotron_h", "nemotron_h_moe", "nemotron_h_omni"}, req.model.Config.ModelFamily) && numParallel != 1 {
 		numParallel = 1
 		slog.Warn("model architecture does not currently support parallel requests", "architecture", req.model.Config.ModelFamily)
 	}