llama.cpp Files

Port of Facebook's LLaMA model in C/C++

This is an exact mirror of the llama.cpp project, hosted at https://github.com/ggml-org/llama.cpp. SourceForge is not affiliated with llama.cpp.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
llama-b9369-xcframework.zip	< 13 hours ago	205.0 MB	0
llama-b9369-ui.tar.gz	< 13 hours ago	1.9 MB	0
llama-b9369-bin-win-vulkan-x64.zip	< 13 hours ago	33.0 MB	0
llama-b9369-bin-win-opencl-adreno-arm64.zip	< 13 hours ago	10.2 MB	0
llama-b9369-bin-win-hip-radeon-x64.zip	< 13 hours ago	319.8 MB	0
llama-b9369-bin-win-cuda-13.3-x64.zip	< 13 hours ago	158.4 MB	0
llama-b9369-bin-win-cuda-12.4-x64.zip	< 13 hours ago	260.2 MB	0
llama-b9369-bin-win-cpu-x64.zip	< 13 hours ago	16.1 MB	0
llama-b9369-bin-win-cpu-arm64.zip	< 13 hours ago	9.7 MB	0
llama-b9369-bin-ubuntu-x64.tar.gz	< 13 hours ago	14.5 MB	0
llama-b9369-bin-ubuntu-vulkan-x64.tar.gz	< 13 hours ago	32.2 MB	0
llama-b9369-bin-ubuntu-vulkan-arm64.tar.gz	< 13 hours ago	25.4 MB	0
llama-b9369-bin-ubuntu-s390x.tar.gz	< 13 hours ago	13.0 MB	0
llama-b9369-bin-ubuntu-rocm-7.2-x64.tar.gz	< 13 hours ago	130.1 MB	0
llama-b9369-bin-ubuntu-openvino-2026.0-x64.tar.gz	< 13 hours ago	12.9 MB	0
llama-b9369-bin-ubuntu-arm64.tar.gz	< 13 hours ago	11.5 MB	0
llama-b9369-bin-macos-x64.tar.gz	< 13 hours ago	9.9 MB	0
llama-b9369-bin-macos-arm64.tar.gz	< 13 hours ago	9.8 MB	0
llama-b9369-bin-android-arm64.tar.gz	< 13 hours ago	73.4 MB	0
cudart-llama-bin-win-cuda-13.3-x64.zip	< 13 hours ago	391.0 MB	0
cudart-llama-bin-win-cuda-12.4-x64.zip	< 13 hours ago	391.4 MB	0
b9369 source code.tar.gz	< 14 hours ago	34.0 MB	0
b9369 source code.zip	< 14 hours ago	35.4 MB	0
README.md	< 14 hours ago	3.1 kB	0
Totals: 24 Items		2.2 GB	0

ggml-webgpu: Fix how to dispatch WG to some ops (#23750)

macOS/iOS:

macOS Apple Silicon (arm64)
macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED
macOS Intel (x64)
iOS XCFramework

Linux:

Android:

Android arm64 (CPU)

Windows:

openEuler:

DISABLED
openEuler x86 (310p)
openEuler x86 (910b, ACL Graph)
openEuler aarch64 (310p)
openEuler aarch64 (910b, ACL Graph)

UI:

UI

Source: README.md, updated 2026-05-27

Other Useful Business Software

Stop Storing Third-Party Tokens in Your Database Icon

Stop Storing Third-Party Tokens in Your Database

Auth0 Token Vault handles secure token storage, exchange, and refresh for external providers so you don't have to build it yourself.

Rolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.

Try Auth0 for Free

Enterprise-grade ITSM, for every business Icon

Enterprise-grade ITSM, for every business

Give your IT, operations, and business teams the ability to deliver exceptional services—without the complexity.

Freshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.

Try it Free

Forever Free Full-Stack Observability | Grafana Cloud

Our generous forever free tier includes the full platform, including the AI Assistant, for 3 users with 10k metrics, 50GB logs, and 50GB traces.

Built on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.

Create free account

Recommended Projects

LLamaSharp
C#/.NET binding of llama.cpp, including LLaMa/GPT model inference
llama.cpp Python Bindings
Python bindings for llama.cpp
Alpaca.cpp
Locally run an Instruction-Tuned Chat-Style LLM
ChatGLM.cpp
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
llama.cpp
LLM inference in C/C++