diff --git a/misc/llama-cpp/Makefile b/misc/llama-cpp/Makefile
index 7141673006e7..6786d3b40280 100644
--- a/misc/llama-cpp/Makefile
+++ b/misc/llama-cpp/Makefile
@@ -1,40 +1,40 @@
 PORTNAME=	llama-cpp
 DISTVERSIONPREFIX=	b
-DISTVERSION=	3078
+DISTVERSION=	3091
 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
 
 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
 OPTIONS_SUB=		yes
 
 EXAMPLES_CMAKE_BOOL=	LLAMA_BUILD_EXAMPLES
 
 BINARY_ALIAS=	git=false
 
 # 1 test fails due to a missing model file (stories260K.gguf)
 
 .include <bsd.port.mk>
diff --git a/misc/llama-cpp/distinfo b/misc/llama-cpp/distinfo
index 4f61bee79768..25bb3d643f9b 100644
--- a/misc/llama-cpp/distinfo
+++ b/misc/llama-cpp/distinfo
@@ -1,5 +1,5 @@
-TIMESTAMP = 1717487081
-SHA256 (ggerganov-llama.cpp-b3078_GH0.tar.gz) = 393137901a7567f92bd25f446efe540c0c97fc464072430af32605f86e27a2c7
-SIZE (ggerganov-llama.cpp-b3078_GH0.tar.gz) = 20572952
+TIMESTAMP = 1717651108
+SHA256 (ggerganov-llama.cpp-b3091_GH0.tar.gz) = bbeffb8753534878c03b347c97c10f3ff1a9369b3ab69018430aabd10d1b50ee
+SIZE (ggerganov-llama.cpp-b3091_GH0.tar.gz) = 20541244
 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 f40b909358db..0b5bc0e84cf6 100644
--- a/misc/llama-cpp/pkg-plist
+++ b/misc/llama-cpp/pkg-plist
@@ -1,46 +1,45 @@
 %%EXAMPLES%%bin/baby-llama
 %%EXAMPLES%%bin/batched
 %%EXAMPLES%%bin/batched-bench
-%%EXAMPLES%%bin/beam-search
 %%EXAMPLES%%bin/benchmark
 %%EXAMPLES%%bin/convert-hf-to-gguf.py
 %%EXAMPLES%%bin/convert-llama2c-to-ggml
 %%EXAMPLES%%bin/embedding
 %%EXAMPLES%%bin/eval-callback
 %%EXAMPLES%%bin/export-lora
 %%EXAMPLES%%bin/finetune
 %%EXAMPLES%%bin/gguf
 %%EXAMPLES%%bin/gguf-split
 %%EXAMPLES%%bin/gritlm
 %%EXAMPLES%%bin/imatrix
 %%EXAMPLES%%bin/infill
 %%EXAMPLES%%bin/llama-bench
 %%EXAMPLES%%bin/llava-cli
 %%EXAMPLES%%bin/lookahead
 %%EXAMPLES%%bin/lookup
 %%EXAMPLES%%bin/lookup-create
 %%EXAMPLES%%bin/lookup-merge
 %%EXAMPLES%%bin/lookup-stats
 %%EXAMPLES%%bin/main
 %%EXAMPLES%%bin/parallel
 %%EXAMPLES%%bin/passkey
 %%EXAMPLES%%bin/perplexity
 %%EXAMPLES%%bin/quantize
 %%EXAMPLES%%bin/quantize-stats
 %%EXAMPLES%%bin/retrieval
 %%EXAMPLES%%bin/save-load-state
 %%EXAMPLES%%bin/server
 %%EXAMPLES%%bin/simple
 %%EXAMPLES%%bin/speculative
 %%EXAMPLES%%bin/tokenize
 %%EXAMPLES%%bin/train-text-from-scratch
 include/ggml-alloc.h
 include/ggml-backend.h
 include/ggml.h
 include/llama.h
 lib/cmake/Llama/LlamaConfig.cmake
 lib/cmake/Llama/LlamaConfigVersion.cmake
 lib/libggml_shared.so
 lib/libllama.so
 %%EXAMPLES%%lib/libllava_shared.so
 libdata/pkgconfig/llama.pc