Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Update README to clarify Darwin kernel versioning
Justine Tunneya56ffd4af838
diff --git a/README.md b/README.mdindex 5423a542..a3b36675 100644--- a/README.md+++ b/README.md@@ -213,7 +213,7 @@ llamafile supports the following operating systems, which require a minimumstock install:- Linux 2.6.18+ (ARM64 or AMD64) i.e. any distro RHEL5 or newer-- macOS 15.6+ (ARM64 or AMD64, with GPU only supported on ARM64)+- Darwin (macOS) 23.1.0+ [1] (ARM64 or AMD64, with GPU only supported on ARM64)- Windows 8+ (AMD64)- FreeBSD 13+ (AMD64, GPU should work in theory)- NetBSD 9.2+ (AMD64, GPU should work in theory)@@ -232,6 +232,9 @@ llamafile supports the following CPUs:Apple Silicon to 64-bit Raspberry Pis will work, provided your weightsfit into memory.+[1] Darwin kernel versions 15.6+ *should* be supported, but we currently+ have no way of testing that.+## GPU supportOn Apple Silicon, everything should just work if Xcode is installed.