Arch Linux User Repository

Search Criteria

Enter search criteria

Search by

Keywords

Out of Date

Sort by

Sort order

Per page

Package Details: intel-llm 0.2.0-2

Package Actions

Git Clone URL:	https://aur.archlinux.org/intel-llm.git (read-only, click to copy)
Package Base:	intel-llm
Description:	One entry point for fast local LLMs on Intel laptops (Arc GPU via official llama-cpp + ggml-sycl, NPU via OpenVINO GenAI)
Upstream URL:	https://github.com/corbet-labs/intel-llm
Licenses:	MIT
Submitter:	richc
Maintainer:	richc
Last Packager:	richc
Votes:	0
Popularity:	0.000000
First Submitted:	2026-07-04 00:45 (UTC)
Last Updated:	2026-09-13 20:27 (UTC)

Dependencies (6)

ggml-sycl
llama-cpp (llama-cpp-rocm-git^AUR, llama.cpp-bin-noavx^AUR, llama.cpp-hip-git^AUR, llama.cpp-hip-gfx1151^AUR, llama-prism-rocm-bin^AUR, llama-prism-cuda^AUR, llama.cpp-gfx1151^AUR)
openvino-genai-bin^AUR
python-huggingface-hub (python-huggingface-hub-git^AUR)
intel-llm-convert^AUR (optional) – convert your own HF models to NPU INT4 IR
intel-npu-driver (intel-npu-driver-git^AUR) (optional) – Intel NPU (AI Boost) for the fast NPU path

Required by (1)

intel-llm-convert (optional)

Sources (3)