llama.cpp

LLM inference in C/C++

ggml / ops / maintainer PRs / dev stats / lib llama API / llama-server REST API

SM75 prefill test

On an NVIDIA CMP 50HX with the Qwen3.8-27B IQ2_XXS GGUF, build-best.sh (GGML_CUDA_FORCE_CUBLAS=ON, GGML_CUDA_SM75_Q8_0_FAST_HALF=ON) measured 764.48 ± 11.67 tokens/s for pp1024, versus 618.29 ± 4.88 tokens/s with forced MMQ (+23.6%). Both builds used GGML_CUDA_SM75_Q8_0_FAST_HALF=ON, 99 GPU layers, FlashAttention, a Q8_0 V cache, and batch and ubatch sizes of 1024. Token generation stayed around 23-24 tokens/s in these runs; the gain was in prefill. Results may differ on other GPUs or models.

This result is for Turing (SM75); it is not a Blackwell result. The SM75 dispatch and Q8 conversion paths do not run on Blackwell.

Build and measure:

./build-best.sh
./build-best/bin/llama-bench \
    -m /path/to/Qwen3.8-27B-UD-IQ2_XXS.gguf \
    -p 1024 -n 0 -b 1024 -ub 1024 -ngl 99 \
    -fa on -ctv q8_0 -r 5

Quick start

A few options to get llama.cpp installed on your machine:

• Visit https://llama.app and follow the instructions
• Run with Docker - see our Docker documentation
• Download pre-built binaries from the releases page
• Build from source by cloning this repository - check out our build guide

Once installed:

# Download and run a model directly from Hugging Face
llama cli -hf ggml-org/Qwen3.5-0.8B-GGUF

# Launch OpenAI-compatible API server
llama serve -hf ggml-org/Qwen3.5-0.8B-GGUF

VLM session with llama cli

Built-in web UI against llama serve

Description

The main goal of llama.cpp is to enable LLM (and VLM) inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.

• Plain C/C++ implementation without any dependencies
• Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks
• AVX, AVX2, AVX512 and AMX support for x86 architectures
• RVV, ZVFH, ZFH, ZICBOP and ZIHINTPAUSE support for RISC-V architectures
• 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory use
• Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD GPUs via HIP and Moore Threads GPUs via MUSA)
• Vulkan and SYCL backend support
• CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity

The llama.cpp project is build on top of the ggml library.

Supported backends

Backend	Target devices
BLAS	All
BLIS	All
CANN	Ascend NPU
CUDA	Nvidia GPU
HIP	AMD GPU
Hexagon	Snapdragon
IBM zDNN	IBM Z & LinuxONE
MUSA	Moore Threads GPU
Metal	Apple Silicon
OpenCL	Adreno GPU
OpenVINO [In Progress]	Intel CPUs, GPUs, and NPUs
RPC	All
SYCL	Intel GPU
VirtGPU	VirtGPU APIR
Vulkan	GPU
WebGPU	All
ZenDNN	AMD CPU

Documentation

Tools

• cli
• completion
• server
• GBNF grammars

Development

• How to build
• Running on Docker
• Build on Android
• Multi-GPU usage
• Performance troubleshooting
• GGML tips & tricks
• XCFramework
• Completions
• Models
• Release process

Contributing

• Contributors can open PRs
• Collaborators will be invited based on contributions
• Maintainers can push to branches in the llama.cpp repo and merge PRs into the master branch
• Any help with managing issues, PRs and projects is very appreciated!
• Read the CONTRIBUTING.md for more information

Acknowledgements

• yhirose/cpp-httplib - Single-header HTTP server, used by llama-server - MIT license
• nothings/stb - Single-header image format decoder, used by multimodal subsystem - Public domain
• nlohmann/json - Single-header JSON library, used by various tools/examples - MIT License
• mackron/miniaudio - Single-header audio format decoder, used by multimodal subsystem - Public domain
• sheredom/subprocess.h - Single-header process launching solution for C and C++ - Public domain