ollama-intel-gpu

ollama-intel-gpu

Docker-Anwendung from SpaceInvaderOne's Repository

Übersicht

Ollama for Intel Arc GPUs (B580, A770, A750, etc.) powered by Intel IPEX-LLM. Drop-in replacement for the standard Ollama container — exposes the same API on port 11434. Requires an Intel Arc GPU

Anforderungen

Intel Arc GPU (B580, A770, A750, or other Arc series) with kernel driver loaded.

Laufzeit-Argumente

Web-UI
http://[IP]:[PORT:11434]/
Netzwerk
bridge
Shell
bash
Privilegiert
false
Extra Params
--device=/dev/dri

Konfiguration der Vorlage

Model StoragePathrw

Path on the host for persistent model storage. Models are large (4-20 GB each).

Ziel
/root/.ollama
Standard
/mnt/user/appdata/ollama-intel-gpu
Wert
/mnt/user/appdata/ollama-intel-gpu
Ollama API PortPorttcp

Port for the Ollama API.

Ziel
11434
Standard
11434
Wert
11434
OLLAMA_ORIGINSVariable

Allowed origins for CORS. Set to * to allow Open WebUI and other frontends to connect.

Standard
*
Wert
*
ONEAPI_DEVICE_SELECTORVariable

Select which Intel GPU to use. Use level_zero:0 for the first GPU. Change only if you have multiple Intel GPUs.

Standard
level_zero:0
Wert
level_zero:0
OLLAMA_NUM_PARALLELVariable

Number of parallel inference requests. Set to 1 for 12 GB VRAM cards (B580). Increase only if you have more VRAM.

Standard
1
Wert
1
OLLAMA_NUM_CTXVariable

Context window size in tokens. Larger values use more VRAM. Default 4096 is a good balance for 12 GB cards.

Standard
4096
Wert
4096
OLLAMA_KEEP_ALIVEVariable

How long to keep a model loaded in VRAM after the last request. Use 5m for 5 minutes, -1 for forever, 0 to unload immediately.

Standard
5m
Wert
5m

Statistik herunterladen

876
Downloads insgesamt

Einzelheiten

Repository
spaceinvaderone/ollama-intel-gpu
Zuletzt aktualisiert2026-03-27
Erstmals gesehen2026-04-03

Führen Sie ollama-intel-gpu auf Unraid aus.

ollama-intel-gpu ist gelistet in Community Apps für Unraid OS. Erkunden Sie Unraid, um einen flexiblen Heimserver, ein NAS oder ein Heimlabor aufzubauen.