---
title: Install llama-cpp on Linux | Snap Store
description: Get the latest version of llama-cpp for Linux - Snap package for llama.cpp
  - LLM inference in C/C++
url: https://snapcraft.io/llama-cpp
---

# llama-cpp

[Talha Can Havadar (tchavadar)](https://snapcraft.io/publisher/tchavadar "View all snaps from Talha Can Havadar (tchavadar)")

* [Talha Can Havadar (tchavadar)](https://snapcraft.io/publisher/tchavadar "View all snaps from Talha Can Havadar (tchavadar)")
* [Development](https://snapcraft.io/search?categories=development)
* [Science](https://snapcraft.io/search?categories=science)

latest/stable v0.6.0

Install latest/stable of llama-cpp

---

**Install using the command line**

```
sudo snap install llama-cpp
```

Don't have snapd? [Get set up for snaps](https://snapcraft.io/docs/installing-snapd).

---

### Package name

* llama-cpp

---

### License

* MIT

---

### Last updated

* 12 October 2026 - latest/stable
* 19 October 2026 - latest/candidate

---

### Source code

* [github.com/talhaHavadar/snap-llama.cpp](https://github.com/talhaHavadar/snap-llama.cpp "https://github.com/talhaHavadar/snap-llama.cpp")
* [github.com/ggml-org/llama.cpp](https://github.com/ggml-org/llama.cpp "https://github.com/ggml-org/llama.cpp")

---

### Report a bug

* [github.com/talhaHavadar/snap-llama.cpp/issues/new/choose](https://github.com/talhaHavadar/snap-llama.cpp/issues/new/choose "https://github.com/talhaHavadar/snap-llama.cpp/issues/new/choose")

---

##### Report a Snap Store violation

* [Report this Snap](https://snapcraft.io/llama-cpp#report-snap-modal)

---

* [Description](https://snapcraft.io/llama-cpp#tab-description)
* [Security](https://snapcraft.io/llama-cpp#tab-security)

#### Snap package for llama.cpp - LLM inference in C/C++

llama.cpp packaged as a snap. The main snap ships a CPU build that
works on any x86\_64 or arm64 machine. Optional snap components add
GPU backends:

sudo snap install llama-cpp # CPU
sudo snap install llama-cpp+hip # add AMD GPU
sudo snap install llama-cpp+cuda # add NVIDIA GPU
sudo snap install llama-cpp+vulkan # add Vulkan GPU (Intel, AMD, etc.)
sudo snap install llama-cpp+opencl # add OpenCL GPU (Adreno, Mali, etc.)
sudo snap install llama-cpp+sycl # add SYCL GPU (Intel)

Select a backend persistently with:

sudo snap set llama-cpp backend={cpu,hip,cuda,vulkan,opencl,sycl,auto} # auto = probe
snap get llama-cpp backend

or override it per invocation with the env var:

LLAMA\_CPP\_BACKEND=cpu llama-cpp cli ...

The llama.cpp web server can also be run using the llama-cpp.server app. This
is disabled by default but can be enabled by running:

snap start --enable llama-cpp.server

By default, no additional arguments are passed to the server, meaning it will
listen on the default port and address. Arguments can be specified by setting
the server-opts configuration value, e.g.:

snap set llama-cpp server-opts="--host 0.0.0.0"

Afterwards, the server must be restarted for the new arguments to take effect:

snap restart llama-cpp.server

---

## Install llama-cpp on your Linux distribution

Choose your Linux distribution to get detailed installation instructions. If yours is not shown, get more details on the [installing snapd documentation](https://snapcraft.io/docs/installing-snapd).

[### Arch Linux](https://snapcraft.io/install/llama-cpp/arch)

[### CentOS](https://snapcraft.io/install/llama-cpp/centos)

[### Debian](https://snapcraft.io/install/llama-cpp/debian)

[### elementary OS](https://snapcraft.io/install/llama-cpp/elementary)

[### Fedora](https://snapcraft.io/install/llama-cpp/fedora)

[### KDE Neon](https://snapcraft.io/install/llama-cpp/kde-neon)

[### Kubuntu](https://snapcraft.io/install/llama-cpp/kubuntu)

[### Manjaro](https://snapcraft.io/install/llama-cpp/manjaro)

[### Pop!\_OS](https://snapcraft.io/install/llama-cpp/pop)

[### openSUSE](https://snapcraft.io/install/llama-cpp/opensuse)

[### Red Hat Enterprise Linux](https://snapcraft.io/install/llama-cpp/rhel)

[### Ubuntu](https://snapcraft.io/install/llama-cpp/ubuntu)

[### Raspberry Pi](https://snapcraft.io/install/llama-cpp/raspbian)