概述

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

要求

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

运行时参数

网络用户界面: http://[IP]:[PORT:11434]/
网络: bridge
外壳: bash
特权: false
额外参数: --device=/dev/dri

模板配置

Model StoragePathrw

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

目标: /root/.ollama
默认值: /mnt/user/appdata/ollama-intel-gpu
价值: /mnt/user/appdata/ollama-intel-gpu

Ollama API PortPorttcp

Port for the Ollama API.

目标: 11434
默认值: 11434
价值: 11434

OLLAMA_ORIGINSVariable

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

默认值: *
价值: *

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.

默认值: level_zero:0
价值: 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.

默认值: 1
价值: 1

OLLAMA_NUM_CTXVariable

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

默认值: 4096
价值: 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.

默认值: 5m
价值: 5m

类别

AI Tools > Utilities

下载统计数据

876

下载总数

链接

模板支持 Docker Hub Pro连接

详细信息

存储库

spaceinvaderone/ollama-intel-gpu

登记处

https://hub.docker.com/r/spaceinvaderone/ollama-intel-gpu/

最后更新2026-03-27

初见2026-04-03

在Unraid 上运行 ollama-intel-gpu 。

ollama-intel-gpu 已被列入Unraid OS 的社区应用程序。探索Unraid ，构建灵活的家庭服务器、NAS 或家庭实验室。

探索Unraid OS