diff --git a/misc/llama-cpp/Makefile b/misc/llama-cpp/Makefile
index 55dfc1bcb378..c2555f13efcf 100644
--- a/misc/llama-cpp/Makefile
+++ b/misc/llama-cpp/Makefile
@@ -1,55 +1,55 @@
 PORTNAME=	llama-cpp
 DISTVERSIONPREFIX=	b
-DISTVERSION=	4419
+DISTVERSION=	4458
 CATEGORIES=	misc # machine-learning
 
 MAINTAINER=	yuri@FreeBSD.org
 COMMENT=	Facebook's LLaMA model in C/C++ # '
 WWW=		https://github.com/ggerganov/llama.cpp
 
 LICENSE=	MIT
 LICENSE_FILE=	${WRKSRC}/LICENSE
 
 BROKEN_armv7=	clang crashes, see https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=278810
 BROKEN_i386=	compilation fails, see https://github.com/ggerganov/llama.cpp/issues/9545
 
 USES=		cmake:testing compiler:c++11-lang python:run shebangfix
 USE_LDCONFIG=	yes
 
 USE_GITHUB=	yes
 GH_ACCOUNT=	ggerganov
 GH_PROJECT=	llama.cpp
 GH_TUPLE=	nomic-ai:kompute:4565194:kompute/kompute
 
 SHEBANG_GLOB=	*.py
 
 CMAKE_ON=	BUILD_SHARED_LIBS
 CMAKE_OFF=	LLAMA_BUILD_TESTS
 CMAKE_TESTING_ON=	LLAMA_BUILD_TESTS
 
 OPTIONS_DEFINE=		CURL EXAMPLES VULKAN
 OPTIONS_DEFAULT=	CURL VULKAN
 OPTIONS_SUB=		yes
 
 CURL_DESCR=		Use libcurl to download model from an URL
 CURL_CMAKE_BOOL=	LLAMA_CURL
 CURL_USES=		localbase
 CURL_LIB_DEPENDS=	libcurl.so:ftp/curl
 
 EXAMPLES_CMAKE_BOOL=	LLAMA_BUILD_EXAMPLES
 
 VULKAN_DESC=		Vulkan GPU offload support
 VULKAN_CMAKE_BOOL=	GGML_VULKAN
 VULKAN_BUILD_DEPENDS=	glslc:graphics/shaderc \
 			vulkan-headers>0:graphics/vulkan-headers
 VULKAN_LIB_DEPENDS=	libvulkan.so:graphics/vulkan-loader
 
 BINARY_ALIAS=	git=false
 
 do-test-ci: # build of tests fails, see https://github.com/ggerganov/llama.cpp/issues/10955
 	@cd ${WRKSRC} && \
 		${SETENV} ${MAKE_ENV} bash ci/run.sh ./tmp/results ./tmp/mnt
 
-# tests as of 4404: 97% tests passed, 1 tests failed out of 31, see https://github.com/ggerganov/llama.cpp/issues/11036
+# tests as of 4458: 97% tests passed, 1 tests failed out of 31, see https://github.com/ggerganov/llama.cpp/issues/11036
 
 .include <bsd.port.mk>
diff --git a/misc/llama-cpp/distinfo b/misc/llama-cpp/distinfo
index 7a00a1575eec..12febbecef6c 100644
--- a/misc/llama-cpp/distinfo
+++ b/misc/llama-cpp/distinfo
@@ -1,5 +1,5 @@
-TIMESTAMP = 1736139395
-SHA256 (ggerganov-llama.cpp-b4419_GH0.tar.gz) = 2071344152c0e685a7e14a9868e977c3ca0f28951621db7e6d1d9ba8d4bf198d
-SIZE (ggerganov-llama.cpp-b4419_GH0.tar.gz) = 20608062
+TIMESTAMP = 1736573693
+SHA256 (ggerganov-llama.cpp-b4458_GH0.tar.gz) = 62e698f1a34e851d448db0d85123bf6f1c3f6eec5a25e29ddc8a4a71aeda5230
+SIZE (ggerganov-llama.cpp-b4458_GH0.tar.gz) = 20428216
 SHA256 (nomic-ai-kompute-4565194_GH0.tar.gz) = 95b52d2f0514c5201c7838348a9c3c9e60902ea3c6c9aa862193a212150b2bfc
 SIZE (nomic-ai-kompute-4565194_GH0.tar.gz) = 13540496
diff --git a/misc/llama-cpp/pkg-plist b/misc/llama-cpp/pkg-plist
index 4becea008f43..134491812ff6 100644
--- a/misc/llama-cpp/pkg-plist
+++ b/misc/llama-cpp/pkg-plist
@@ -1,66 +1,67 @@
 bin/convert_hf_to_gguf.py
 %%EXAMPLES%%bin/llama-batched
 %%EXAMPLES%%bin/llama-batched-bench
 %%EXAMPLES%%bin/llama-bench
 %%EXAMPLES%%bin/llama-cli
 %%EXAMPLES%%bin/llama-convert-llama2c-to-ggml
 %%EXAMPLES%%bin/llama-cvector-generator
 %%EXAMPLES%%bin/llama-embedding
 %%EXAMPLES%%bin/llama-eval-callback
 %%EXAMPLES%%bin/llama-export-lora
-%%EXAMPLES%%bin/llama-gen-docs
 %%EXAMPLES%%bin/llama-gbnf-validator
+%%EXAMPLES%%bin/llama-gen-docs
 %%EXAMPLES%%bin/llama-gguf
 %%EXAMPLES%%bin/llama-gguf-hash
 %%EXAMPLES%%bin/llama-gguf-split
 %%EXAMPLES%%bin/llama-gritlm
 %%EXAMPLES%%bin/llama-imatrix
 %%EXAMPLES%%bin/llama-infill
 %%EXAMPLES%%bin/llama-llava-cli
 %%EXAMPLES%%bin/llama-lookahead
 %%EXAMPLES%%bin/llama-lookup
 %%EXAMPLES%%bin/llama-lookup-create
 %%EXAMPLES%%bin/llama-lookup-merge
 %%EXAMPLES%%bin/llama-lookup-stats
 %%EXAMPLES%%bin/llama-minicpmv-cli
 %%EXAMPLES%%bin/llama-parallel
 %%EXAMPLES%%bin/llama-passkey
 %%EXAMPLES%%bin/llama-perplexity
 %%EXAMPLES%%bin/llama-quantize
 %%EXAMPLES%%bin/llama-quantize-stats
 %%EXAMPLES%%bin/llama-qwen2vl-cli
 %%EXAMPLES%%bin/llama-retrieval
 %%EXAMPLES%%bin/llama-run
 %%EXAMPLES%%bin/llama-save-load-state
 %%EXAMPLES%%bin/llama-server
 %%EXAMPLES%%bin/llama-simple
 %%EXAMPLES%%bin/llama-simple-chat
 %%EXAMPLES%%bin/llama-speculative
 %%EXAMPLES%%bin/llama-speculative-simple
 %%EXAMPLES%%bin/llama-tokenize
 %%EXAMPLES%%bin/llama-tts
 %%VULKAN%%bin/vulkan-shaders-gen
 include/ggml-alloc.h
 include/ggml-backend.h
 include/ggml-blas.h
 include/ggml-cann.h
 include/ggml-cpu.h
 include/ggml-cuda.h
 include/ggml-kompute.h
 include/ggml-metal.h
 include/ggml-opt.h
 include/ggml-rpc.h
 include/ggml-sycl.h
 include/ggml-vulkan.h
 include/ggml.h
+include/gguf.h
 include/llama-cpp.h
 include/llama.h
 lib/cmake/llama/llama-config.cmake
 lib/cmake/llama/llama-version.cmake
 lib/libggml-base.so
 lib/libggml-cpu.so
 %%VULKAN%%lib/libggml-vulkan.so
 lib/libggml.so
 lib/libllama.so
 %%EXAMPLES%%lib/libllava_shared.so
 libdata/pkgconfig/llama.pc