Item detail

eleiton/ollama-intel-arc

ollama-intel-arc is an Apache-2.0 Docker Compose stack that makes Intel Arc GPUs (the discrete Intel graphics line, not the integrated ones) useful for running Ollama, Stable Diffusion / ComfyUI / SD.Next, and OpenAI Whisper on Linux. 359 stars, uses Intel Extension for PyTorch (IPEX-LLM) underneath, ships tested container configs for each tool, exposes standard ports (11434 for Ollama, 7860 for O

Score7.4
Popularity58.0
Risknone
TierSilver
Score breakdown
Usefulness7.0
Novelty7.0
Momentum6.0
Maturity6.6
Open-source/build8.4
Evidence7.2
Workflow potential7.8
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for Linux users on Intel Arc GPUs (A-series discrete, B-series) who have been locked out of the local-LLM ecosystem because most stacks target NVIDIA. `git clone && podman compose up` gives you Ollama, Open WebUI, ComfyUI / SD.Next, and Whisper, all wired to use the Arc GPU via IPEX-LLM. Pre-1.0 IPEX-LLM and Intel's own XPU drivers mean the surface is rougher than NVIDIA, so this is a `watc

Who should use it

Linux users on Intel Arc discrete GPUs (A-series, B-series) who want local LLM / SD / Whisperdevelopers who have an Arc card from a previous build and want to repurpose it for AI workloadsanyone locked out of the NVIDIA-only local-LLM ecosystem who wants a tested Compose stacktinkerers evaluating IPEX-LLM as an alternative to CUDA for personal AI infra

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

IPEX-LLM is pre-1.0 and Intel's XPU driver stack is a moving target — expect breakages on kernel / driver updates; Performance is generally below comparable NVIDIA setups; treat this as a 'make it work' option, not a 'make it fast' option.

Evidence links

Closest alternatives / related signals

intel-arcintel-gpuollamastable-diffusionwhispercomfyuiipex-llmdocker-compose