github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3517] MACOS M2 Docker Compose Failing with GPU Selection Step #2169

New Issue
Closed
opened 2026-04-12 12:25:02 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 12:25:02 -05:00
Owner
Copy Link

Originally created by @akramIOT on GitHub (Apr 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3517

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

MACOS M2 Docker Compose Failing with GPU Selection Step

(LLAMA_CPP_ENV) akram_personal@AKRAMs-MacBook-Pro packet_raptor % docker-compose up
Attaching to packet_raptor, ollama-1, ollama-webui-1
Gracefully stopping... (press Ctrl+C again to force)
Error response from daemon: could not select device driver "nvidia" with capabilities: gpu
(LLAMA_CPP_ENV) akram_personal@AKRAMs-MacBook-Pro packet_raptor %

What did you expect to see?

No response

Steps to reproduce

No response

Are there any recent changes that introduced the issue?

No response

OS

macOS

Architecture

arm64

Platform

Docker

Ollama version

0.1.30

GPU

Apple

GPU info

(base) akram_personal@AKRAMs-MacBook-Pro ~ % ioreg -l | grep num_cores
| | | | "GPUConfigurationVariable" = {"num_gps"=8,"gpu_gen"=14,"usc_gen"=2,"num_cores"=20,"num_mgpus"=2,"core_mask_list"=(1023,511),"num_frags"=20}
(base) akram_personal@AKRAMs-MacBook-Pro ~ %
(base) akram_personal@AKRAMs-MacBook-Pro ~ %
(base) akram_personal@AKRAMs-MacBook-Pro ~ % system_profiler SPDisplaysDataType
Graphics/Displays:

Apple M2 Pro:

  Chipset Model: Apple M2 Pro
  Type: GPU
  Bus: Built-In
  Total Number of Cores: 19
  Vendor: Apple (0x106b)
  Metal Support: Metal 3
  Displays:
    Color LCD:
      Display Type: Built-in Liquid Retina XDR Display
      Resolution: 3456 x 2234 Retina
      Main Display: Yes
      Mirror: Off
      Online: Yes
      Automatically Adjust Brightness: Yes
      Connection Type: Internal
    VX2757:
      Resolution: 1920 x 1080 (1080p FHD - Full High Definition)
      UI Looks like: 1920 x 1080 @ 75.00Hz
      Mirror: Off
      Online: Yes
      Rotation: Supported

(base) akram_personal@AKRAMs-MacBook-Pro ~ %

root:xnu-10002.81.5~7/RELEASE_ARM64_T6020 arm64

CPU

Apple

Other software

No response

Originally created by @akramIOT on GitHub (Apr 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3517 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? MACOS M2 Docker Compose Failing with GPU Selection Step (LLAMA_CPP_ENV) akram_personal@AKRAMs-MacBook-Pro packet_raptor % docker-compose up Attaching to packet_raptor, ollama-1, ollama-webui-1 Gracefully stopping... (press Ctrl+C again to force) Error response from daemon: could not select device driver "nvidia" with capabilities: [[gpu]] (LLAMA_CPP_ENV) akram_personal@AKRAMs-MacBook-Pro packet_raptor % ### What did you expect to see? _No response_ ### Steps to reproduce _No response_ ### Are there any recent changes that introduced the issue? _No response_ ### OS macOS ### Architecture arm64 ### Platform Docker ### Ollama version 0.1.30 ### GPU Apple ### GPU info (base) akram_personal@AKRAMs-MacBook-Pro ~ % ioreg -l | grep num_cores | | | | "GPUConfigurationVariable" = {"num_gps"=8,"gpu_gen"=14,"usc_gen"=2,"num_cores"=20,"num_mgpus"=2,"core_mask_list"=(1023,511),"num_frags"=20} (base) akram_personal@AKRAMs-MacBook-Pro ~ % (base) akram_personal@AKRAMs-MacBook-Pro ~ % (base) akram_personal@AKRAMs-MacBook-Pro ~ % system_profiler SPDisplaysDataType Graphics/Displays: Apple M2 Pro: Chipset Model: Apple M2 Pro Type: GPU Bus: Built-In Total Number of Cores: 19 Vendor: Apple (0x106b) Metal Support: Metal 3 Displays: Color LCD: Display Type: Built-in Liquid Retina XDR Display Resolution: 3456 x 2234 Retina Main Display: Yes Mirror: Off Online: Yes Automatically Adjust Brightness: Yes Connection Type: Internal VX2757: Resolution: 1920 x 1080 (1080p FHD - Full High Definition) UI Looks like: 1920 x 1080 @ 75.00Hz Mirror: Off Online: Yes Rotation: Supported (base) akram_personal@AKRAMs-MacBook-Pro ~ % root:xnu-10002.81.5~7/RELEASE_ARM64_T6020 arm64 ### CPU Apple ### Other software _No response_
GiteaMirror added the needs more info label 2026-04-12 12:25:02 -05:00
GiteaMirror commented 2026-04-12 12:25:03 -05:00
Author
Owner
Copy Link

@akramIOT commented on GitHub (Apr 7, 2024):

Docker Compose YAML File:

Version: '3.6'

networks:
ollama:

services:
ollama:
image: ollama/ollama
networks:
- ollama
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
volumes:
- ./data/ollama:/root/.ollama
ports:
- 11434:11434

ollama-webui:
image: ghcr.io/ollama-webui/ollama-webui:main
volumes:
- ./data/ollama-webui:/app/backend/data
depends_on:
- ollama
ports:
- 3002:8080
environment:
- 'OLLAMA_API_BASE_URL=http://ollama:11434/api'
extra_hosts:
- host.docker.internal:host-gateway
networks:
- ollama

packet_raptor:
build:
context: ./
dockerfile: ./docker/Dockerfile # Specify the path to your existing Dockerfile
container_name: packet_raptor
restart: always
ports:
- "8585:8585"
volumes:
- ./config.toml:/root/.streamlit/config.toml
environment:
- OLLAMA_URL=http://ollama:11434
depends_on:
- ollama
networks:
- ollama
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [ gpu ]

volumes:
ollama: {}

<!-- gh-comment-id:2041238255 --> @akramIOT commented on GitHub (Apr 7, 2024): Docker Compose YAML File: Version: '3.6' networks: ollama: services: ollama: image: ollama/ollama networks: - ollama deploy: resources: reservations: devices: - driver: nvidia count: 1 capabilities: [gpu] volumes: - ./data/ollama:/root/.ollama ports: - 11434:11434 ollama-webui: image: ghcr.io/ollama-webui/ollama-webui:main volumes: - ./data/ollama-webui:/app/backend/data depends_on: - ollama ports: - 3002:8080 environment: - 'OLLAMA_API_BASE_URL=http://ollama:11434/api' extra_hosts: - host.docker.internal:host-gateway networks: - ollama packet_raptor: build: context: ./ dockerfile: ./docker/Dockerfile # Specify the path to your existing Dockerfile container_name: packet_raptor restart: always ports: - "8585:8585" volumes: - ./config.toml:/root/.streamlit/config.toml environment: - OLLAMA_URL=http://ollama:11434 depends_on: - ollama networks: - ollama deploy: resources: reservations: devices: - driver: nvidia count: 1 capabilities: [ gpu ] volumes: ollama: {}
GiteaMirror commented 2026-04-12 12:25:03 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 12, 2024):

If I understand correctly, you're trying to use Docker Desktop on an ARM Mac system to run Ollama. This will only work with CPU mode. Apple systems do not have NVIDIA GPUs, they have Apple GPUs, and Docker Desktop does not expose the GPU to the container. If you remove the GPU settings so it runs CPU only, then it should work, but you'll be getting ARM CPU based execution. You'll see much better performance if you stick with running on the native Mac where the mac binary of Ollama can leverage the GPU.

<!-- gh-comment-id:2052680938 --> @dhiltgen commented on GitHub (Apr 12, 2024): If I understand correctly, you're trying to use Docker Desktop on an ARM Mac system to run Ollama. This will only work with CPU mode. Apple systems do not have NVIDIA GPUs, they have Apple GPUs, and Docker Desktop does not expose the GPU to the container. If you remove the GPU settings so it runs CPU only, then it should work, but you'll be getting ARM CPU based execution. You'll see much better performance if you stick with running on the native Mac where the mac binary of Ollama can leverage the GPU.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label needs more info
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2169
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?