From b3ce5cedf4c007b78a45befe839fa3abada03c0b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sigbj=C3=B8rn=20Skj=C3=A6ret?=
 <1629204+CISC@users.noreply.github.com>
Date: Thu, 25 Jun 2026 07:36:49 +0200
Subject: [PATCH] quant : fix quantizing moe with mtp (#24986)

---
 src/llama-quant.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/llama-quant.cpp b/src/llama-quant.cpp
index 89b7fe8d43..847e79f465 100644
--- a/src/llama-quant.cpp
+++ b/src/llama-quant.cpp
@@ -847,7 +847,7 @@ static void init_quantize_state_counters(quantize_state_impl & qs, std::vector<t
             qs.has_tied_embeddings = false;
         }
     }
-    qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer();
+    qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)qs.model.hparams.n_layer_all;
 }
 
 //