Sign inSign up

dosperado74/ollarc-intel

By dosperado74

•Updated 6 days ago

Upstream Ollama accelerated on Intel Arc / Xe GPUs (iGPU + dGPU) via llama.cpp SYCL

Image
Machine learning & AI
1

592

dosperado74/ollarc-intel repository overview

⁠ollarc-intel

The current upstream Ollama⁠, accelerated on Intel GPUs through the llama.cpp SYCL backend (oneAPI / Level Zero).

Normal Ollama (ollama pull, ollama run, the API, Open WebUI), but with a SYCL GPU backend for Intel Arc / Xe iGPUs (Meteor Lake, Arrow Lake, Lunar Lake) and dedicated Arc cards (A-series, B-series). Rebuilt automatically for every new Ollama release.

Source, docs and issues: https://github.com/Dosperado74/ollarc-intel⁠

This page is generated from docs/dockerhub.md⁠. The same images are also published as ghcr.io/dosperado74/ollarc-intel.

⁠Performance

ASUS NUC 14 Pro+, Core Ultra 9 285H (Arc 140T iGPU), tag latest-arl-h, 100 % GPU:

ModelPrefillDecode
llama3.2:3b (Q4_K_M)1249 tok/s26.1 tok/s
gpt-oss:20b (MXFP4)288 – 1106 tok/s14.0 tok/s
gemma4:e4b361 tok/s16.1 tok/s
gemma-4-26B-A4B-it-qat-q4_0 (MoE)184 tok/s14.6 tok/s

More numbers and how they were measured: README⁠.

⁠Quick start

The host needs a recent kernel (Arrow Lake ≥ 6.11) and the Intel GPU firmware (Debian: firmware-intel-graphics; Ubuntu, Fedora, Proxmox VE: already included). ls /dev/dri must show renderD128. Details: host setup⁠.

docker run -d --name ollama --restart unless-stopped \
  --device /dev/dri \
  --group-add "$(stat -c %g /dev/dri/renderD128)" \
  -v ollama:/root/.ollama -p 11434:11434 \
  dosperado74/ollarc-intel:latest

docker exec ollama ollama run llama3.2:3b
docker exec ollama ollama ps        # -> PROCESSOR 100% GPU

With Open WebUI: use the docker-compose.yml⁠ from the repository. Proxmox VE LXC: Proxmox guide⁠.

⁠Tags

TagKernelsFor
latestJIT (SPIR-V)recommended, every supported Intel GPU
latest-arl-hAOT arl-hArrow Lake-H iGPU (Core Ultra 200H, Arc 140T / 130T)
latest-dg2AOT acm-g10,acm-g11dedicated Arc A-series (A770, A750, A580, A380, A310)
latest-bmgAOT bmg-g21dedicated Arc B-series (B580, B570, Arc Pro B50 / B60)

Every tag also exists per Ollama version, e.g. 0.40.15, 0.40.15-arl-h. AOT images only shorten the first model load; inference speed is the same as JIT.

⁠Help

MIT license. Not affiliated with Ollama or Intel.

Tag summary

Content type

Image

Digest

sha256:a61ee54eb…

Size

2.3 GB

Last updated

6 days ago

docker pull dosperado74/ollarc-intel