diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index 48f52b0e26..94527c14fa 100755
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -6672,7 +6672,6 @@ class FalconH1Model(Mamba2Model):
 
 
         # Add Falcon Mamba2 specific configuration
-        self.gguf_writer.add_uint32("falcon_h1.ssm.mamba_chunk_size", self.hparams["mamba_chunk_size"])
         self.gguf_writer.add_uint32("falcon_h1.attention.head_dim", self.hparams["head_dim"])
         self.gguf_writer.add_uint32("falcon_h1.ssm.mamba_d_ssm", self.hparams["mamba_d_ssm"])
         self.gguf_writer.add_uint32("falcon_h1.num_attention_heads", self.find_hparam(["num_attention_heads"]))
diff --git a/src/llama-arch.h b/src/llama-arch.h
index 80af422361..1dcd135ff7 100644
--- a/src/llama-arch.h
+++ b/src/llama-arch.h
@@ -165,7 +165,6 @@ enum llm_kv {
     LLM_KV_FALCON_H1_USE_MLP,
     LLM_KV_FALCON_H1_MAMBA_NORM_BEFORE_GATE,
     LLM_KV_FALCON_H1_MAMBA_RMS_NORM,
-    LLM_KV_FALCON_H1_MAMBA_CHUNK_SIZE,
 
     LLM_KV_ROPE_DIMENSION_COUNT,
     LLM_KV_ROPE_DIMENSION_SECTIONS,
diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index bf6613a80e..d5b080b3c2 100644
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -1563,7 +1563,6 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                 ml.get_key(LLM_KV_SSM_TIME_STEP_RANK, hparams.ssm_dt_rank);
                 ml.get_key(LLM_KV_SSM_GROUP_COUNT,    hparams.ssm_n_group);
                 ml.get_key(LLM_KV_SSM_HEAD_DIM,       hparams.ssm_head_dim);
-                ml.get_key(LLM_KV_FALCON_H1_MAMBA_CHUNK_SIZE, hparams.chunk_size);
 
                 // Falcon-H1 parameters
                 ml.get_key(LLM_KV_ATTN_HEAD_DIM,      hparams.attn_head_dim);