diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py
index d24d10dcb..85af29549 100644
--- a/gguf-py/gguf/tensor_mapping.py
+++ b/gguf-py/gguf/tensor_mapping.py
@@ -91,7 +91,7 @@ class TensorNameMap:
             "model.layers.layers.{bid}.norm",                       # plamo
             "model.layers.{bid}.attention_norm",                    # internlm2
             "model.layers.{bid}.norm",                              # mamba
-            "backbone.layers.{bid}.mixer.norm",                     # mamba
+            "backbone.layers.{bid}.norm",                           # mamba
         ),
 
         # Attention norm 2
diff --git a/llama.cpp b/llama.cpp
index bbf16e8f4..9dba8eeb2 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -11718,6 +11718,12 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
         quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_POS_EMBD,    "weight");
         quantize &= name != LLM_TN(model.arch)(LLM_TENSOR_TOKEN_TYPES, "weight");
 
+        // do not quantize Mamba's small yet 2D weights
+        // NOTE: can't use LLM_TN here because the layer number is not known
+        quantize &= name.find("ssm_conv1d.weight") == std::string::npos;
+        quantize &= name.find("ssm_x.weight") == std::string::npos;
+        quantize &= name.find("ssm_dt.weight") == std::string::npos;
+
         enum ggml_type new_type;
         void * new_data;
         size_t new_size;