diff --git a/misc/llama-cpp/Makefile b/misc/llama-cpp/Makefile
index d366f823d788..265cb9bc7fb3 100644
--- a/misc/llama-cpp/Makefile
+++ b/misc/llama-cpp/Makefile
@@ -1,49 +1,45 @@
 PORTNAME=	llama-cpp
 DISTVERSIONPREFIX=	b
-DISTVERSION=	3542
+DISTVERSION=	3560
 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
 
-LIB_DEPENDS=	libvulkan.so:graphics/vulkan-loader
-
 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
 
-LDFLAGS+=	-pthread
-
 OPTIONS_DEFINE=		EXAMPLES VULKAN
 OPTIONS_DEFAULT=	VULKAN
 OPTIONS_SUB=		yes
 
 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
 
 # 2 tests fail: https://github.com/ggerganov/llama.cpp/issues/8906
 
 .include <bsd.port.mk>
diff --git a/misc/llama-cpp/distinfo b/misc/llama-cpp/distinfo
index 57bc61877f32..13c27e8f340b 100644
--- a/misc/llama-cpp/distinfo
+++ b/misc/llama-cpp/distinfo
@@ -1,5 +1,5 @@
-TIMESTAMP = 1723097492
-SHA256 (ggerganov-llama.cpp-b3542_GH0.tar.gz) = 6f8b23d930400fce5708d2c85022ef33f1083af8f6ac395abefadacee0942e78
-SIZE (ggerganov-llama.cpp-b3542_GH0.tar.gz) = 19014348
+TIMESTAMP = 1723230415
+SHA256 (ggerganov-llama.cpp-b3560_GH0.tar.gz) = c61f0fd2ed3f83c7a9775343c5a72cb3c7ca61630553fdb495220ad80ca063ed
+SIZE (ggerganov-llama.cpp-b3560_GH0.tar.gz) = 19029390
 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 7d7cc039fb51..22ca598402bf 100644
--- a/misc/llama-cpp/pkg-plist
+++ b/misc/llama-cpp/pkg-plist
@@ -1,55 +1,56 @@
 bin/convert_hf_to_gguf.py
 bin/llama-baby-llama
 bin/llama-batched
 bin/llama-batched-bench
 bin/llama-bench
 bin/llama-bench-matmult
 bin/llama-cli
 bin/llama-convert-llama2c-to-ggml
 bin/llama-cvector-generator
 bin/llama-embedding
 %%EXAMPLES%%bin/llama-eval-callback
 %%EXAMPLES%%bin/llama-export-lora
 %%EXAMPLES%%bin/llama-gbnf-validator
 %%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-retrieval
 %%EXAMPLES%%bin/llama-save-load-state
 %%EXAMPLES%%bin/llama-server
 %%EXAMPLES%%bin/llama-simple
 %%EXAMPLES%%bin/llama-speculative
 %%EXAMPLES%%bin/llama-tokenize
 %%VULKAN%%bin/vulkan-shaders-gen
 include/ggml-alloc.h
 include/ggml-backend.h
 include/ggml-blas.h
 include/ggml-cann.h
 include/ggml-cuda.h
 include/ggml-kompute.h
 include/ggml-metal.h
 include/ggml-rpc.h
 include/ggml-sycl.h
 include/ggml-vulkan.h
 include/ggml.h
 include/llama.h
 lib/cmake/llama/llama-config.cmake
 lib/cmake/llama/llama-version.cmake
 lib/libggml.so
 lib/libllama.so
 %%EXAMPLES%%lib/libllava_shared.so
 libdata/pkgconfig/llama.pc