nemotron-h: distinguish Nemotron 3 Puzzle (75B.A9B) from Super (120B.A12B)

Both have 88 layers; the per-layer expert_used_count array (heterogeneous
for Puzzle, broadcast-uniform for Super) is the discriminator.

src/llama-model.cpp

@@ -810,6 +810,7 @@ const char * llm_type_name(llm_type type) {
         case LLM_TYPE_31B_A3_5B:     return "31B.A3.5B";
         case LLM_TYPE_35B_A3B:       return "35B.A3B";
         case LLM_TYPE_48B_A3B:       return "48B.A3B";
+        case LLM_TYPE_75B_A9B:       return "75B.A9B";
         case LLM_TYPE_80B_A3B:       return "80B.A3B";
         case LLM_TYPE_100B_A6B:      return "100B.A6B";
         case LLM_TYPE_102B_A12B:     return "102B.A12B";

src/llama-model.h

@@ -126,6 +126,7 @@ enum llm_type {
     LLM_TYPE_31B_A3_5B,
     LLM_TYPE_35B_A3B, // Qwen3.5
     LLM_TYPE_48B_A3B, // Kimi Linear
+    LLM_TYPE_75B_A9B, // Nemotron 3 Puzzle
     LLM_TYPE_80B_A3B, // Qwen3 Next
     LLM_TYPE_100B_A6B,
     LLM_TYPE_102B_A12B, // Solar-Open

src/models/nemotron-h.cpp

@@ -42,7 +42,17 @@ void llama_model_nemotron_h::load_arch_hparams(llama_model_loader & ml) {
     switch (hparams.n_layer()) {
         case 52: type = LLM_TYPE_31B_A3_5B; break; // Nemotron-H_MOE 31B
         case 56: type = LLM_TYPE_9B; break;
-        case 88: type = LLM_TYPE_120B_A12B; break;
+        case 88:
+            {
+                // Nemotron 3 Super (uniform MoE) and Nemotron 3 Puzzle (per-layer
+                // heterogeneous MoE) both have 88 layers; the per-layer top-k array
+                // is the discriminator.
+                bool heterogeneous = false;
+                for (uint32_t i = 1; i < hparams.n_layer(); ++i) {
+                    heterogeneous |= hparams.n_expert_used_arr[i] != hparams.n_expert_used_arr[0];
+                }
+                type = heterogeneous ? LLM_TYPE_75B_A9B : LLM_TYPE_120B_A12B;
+            } break;
         default: type = LLM_TYPE_UNKNOWN;
     }
 }