Indholdet er maskineoversat. Se Ansvarsfraskrivelse for maskinoversættelse.

How to deploy Ollama on the QNAP NAS using Container Station

Sådan implementeres Ollama på QNAP NAS ved hjælp af Container Station

Last modified date: 2026-05-08

Applicable Products

QTS, QuTS hero

Container Station

Scenario

You want to run large language models (LLMs) locally on your QNAP NAS for private AI chat, code assistance, or document analysis without sending data to the cloud. Ollama is the most popular and beginner-friendly inference engine for this purpose. This tutorial explains how to deploy Ollama on the QNAP NAS using Container Station.

System Requirements

Requirement	Detail
QNAP App	Container Station 3.x or later
NAS Architecture	x86_64 (Intel or AMD CPU) (Only a few ARM-based models are supported.)
Memory	At least 8 GB (for 3B models) At least 16 GB (for 7B models)
Storage Space	At least 20 GB of extra free storage space in addition to the model file size. Use an SSD volume if possible.
GPU (Optional)	Compatible NVIDIA GPUs (see the compatibility list) GPU should be set to Container Station Mode in the Control Panel.

Warning

OOM (Out of Memory) Risk
Ollama will attempt to load the entire model into memory by default. If your NAS has only 8–16 GB of RAM, loading a 14B or larger model may exhaust system memory, causing NAS services to become unresponsive or the system to restart.

Data Loss Risk
If you do not mount a persistent volume for /root/.ollama, all downloaded models and configuration will be lost when the container is removed or recreated. Always follow the volume mounting instructions in this tutorial.

Best Practice

Check the model size against your available RAM in advance.
Set memory limits to cap container memory usage.
Start with small models (1B or 3B) and assess system stability before attempting larger models.

Procedure

Method 1: CPU-Only Deployment (No GPU Required)

Create storage folders.
Open File Station and create the following folder to store Ollama model data:
/share/Container/ollama
Screenshot: File Station — creating the Ollama folder under /share/Container/
Best Practice
If your NAS has an NVMe SSD cache or SSD volume, create this folder on the SSD. Model loading speed improves by up to 10 times compared to HDDs.

Create a Docker Compose file.

In Container Station, go to Applications > Create. Name the application ollama and paste the following YAML:

version: "3.8"

services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    volumes:
      - /share/Container/ollama:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_KEEP_ALIVE=10m
    networks:
      - ai-network

networks:
  ai-network:
    name: ai-network
    driver: bridge

Screenshot: Container Station — Application creation screen with YAML editor
Screenshot: Container Station — Set the memory limit

Deploy the container.
Click Create. Container Station will pull the Ollama image and start the container. Wait until the status shows Running.
Screenshot: Container Station — ollama container showing "Running" status
Pull your first model.
Open the container's Terminal (or SSH into your NAS and exec you Docker) and run:
```
# For a lightweight 3B model (recommended for first test):
ollama pull llama3.2:3b

# For a standard 9B model (requires 16 GB+ RAM):
ollama pull qwen3.5:9b
```
The download may take several minutes depending on your internet speed. A 9B Q4_K_M model is approximately 4–7 GB.
Note
- Verify you have sufficient disk space before pulling. Use ollama list to check existing models and their sizes.
- For ARM-based NAS models, we recommend starting with the <1B model to monitor memory usage.
Test the model.
In the container terminal, run:
```
ollama run qwen3.5:9b
```
Type a prompt and confirm that you receive a response. Type /bye to exit.

Method 2: NVIDIA GPU-Accelerated Deployment

Note

Additional prerequisites for GPU Mode:

NVIDIA GPU installed and detected by QTS/QuTS hero
GPU set to Container Station Mode in the Control Panel
NVIDIA GPU Driver and NvKernelDriver installed from App Center

Use the GPU-enabled Docker Compose configuration.

Replace the YAML from Method 1 with the following:

version: "3.8"

services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    volumes:
      - /share/Container/ollama:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_KEEP_ALIVE=10m
      - NVIDIA_VISIBLE_DEVICES=all
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - ai-network

networks:
  ai-network:
    name: ai-network
    driver: bridge

Screenshot: Container Station — GPU-enabled Docker Compose YAML

Note

QNAP's bundled NVIDIA drivers may be older than the latest release. If the container fails to start with GPU enabled, check the driver version with nvidia-smi on the host and ensure it is compatible with the Ollama image version

Deploy and verify GPU access.
After the container starts, open its terminal and run:
```
nvidia-smi
```
You should see your GPU model, driver version, and memory information.
Pull a model and confirm GPU acceleration.
```
ollama pull qwen3.5:9b
ollama run qwen3.5:9b
```
While the model is generating a response, open another terminal and run nvidia-smi. You should observe GPU memory usage and GPU utilization increasing.

Result

After completing this tutorial, you will have:

Ollama running on your QNAP NAS at http://<NAS-IP>:11434
Model data persisted in /share/Container/ollama (survives container rebuilds)
A working LLM accessible via the Ollama API

You can test the API from any device on your local network:

curl http://<NAS-IP>:11434/api/generate -d '{
  "model": "qwen3.5:9b",
  "prompt": "Hello, how are you?",
  "stream": false
}'

Important

The OLLAMA_HOST=0.0.0.0 setting exposes the Ollama API on all network interfaces. Do not expose port 11434 to the internet. Use firewall rules or QNAP's network settings to restrict access to your local network only.

Troubleshooting

Container exits immediately after starting

This may be caused by insufficient RAM or GPU driver mismatch. Check container logs in Container Station. Reduce memory limitations or disable GPU mode.

Model pull fails midway

This may result from insufficient disk space or network timeout. Try to free up storage space. Re-run ollama pull; the system resumes from where it stopped.

Response speed is very slow (1–3 tokens per second)

The model may be running on CPU instead of GPU, or the model is too large for your RAM. Verify your GPU access with nvidia-smi inside the container. Try to use a smaller model.

The NAS becomes unresponsive during inference

This can be an "out of memory" issue: the model is consuming all the system memory. We recommend restarting the NAS. Set a memory usage limit in the application. Or use a smaller model.

"Cannot connect to Ollama" message from Open WebUI

This may be caused by a wrong API URL or Docker network isolation. You can use http://ollama:11434 if you are on the same Docker network.

Anvendelige produkter

QTS, QuTS hero

Container Station

Scenario

Du ønsker at køre store sprogmodeller (LLM'er) lokalt på din QNAP NAS til privat AI-chat, kodeassistance eller dokumentanalyse uden at sende data til skyen. Ollama er den mest populære og brugervenlige inferensmotor til dette formål. Denne vejledning forklarer, hvordan man implementerer Ollama på QNAP NAS ved hjælp af Container Station.

Systemkrav

Krav	Detalje
QNAP-app	Container Station 3.x eller nyere
NAS-arkitektur	x86_64 (Intel eller AMD CPU) (Kun få ARM-baserede modeller understøttes.)
Hukommelse	Mindst 8 GB (for 3B-modeller) Mindst 16 GB (for 7B-modeller)
Lager plads	Mindst 20 GB ekstra ledig Lager plads ud over modellens filstørrelse. Brug en SSD-enhed, hvis muligt.
GPU (valgfri)	Kompatible NVIDIA GPU'er (se Kompatibilitetsliste) GPU bør indstilles til Container Station-tilstand i Kontrolpanel.

Advarsel

OOM (Out of Memory) risiko
Ollama vil forsøge at indlæse hele modellen i hukommelsen som standard. Hvis din NAS kun har 8–16 GB RAM, kan indlæsning af en 14B eller større model udtømme systemhukommelsen, hvilket får NAS-tjenester til at blive uresponsive eller systemet til at genstarte.

Risiko for datatab
Hvis du ikke monterer et vedvarende volumen til /root/.ollama, vil alle downloadede modeller og konfigurationer gå tabt, når containeren fjernes eller genskabes. Følg altid instruktionerne for volumenmontering i denne vejledning.

Bedste praksis

Tjek modelstørrelsen i forhold til din tilgængelige RAM på forhånd.
Indstil hukommelsesgrænser for at begrænse containerens hukommelsesforbrug.
Start med små modeller (1B eller 3B) og vurder systemets stabilitet, før du forsøger større modeller.

Procedure

Metode 1: Kun CPU-udrulning (Ingen GPU påkrævet)

Opret Lager-mapper.
Åbn File Station og opret følgende mappe til at gemme Ollama-modeldata:
/share/Container/ollama
Skærmbillede: File Station — oprettelse af Ollama-mappen under /share/Container/
Bedste praksis
Hvis din NAS har en NVMe SSD-cache eller SSD-enhed, skal du oprette denne mappe på SSD'en. Modellastningshastigheden forbedres med op til 10 gange sammenlignet med HDD'er.

Opret en Docker Compose-fil.

I Container Station, gå til Applikationer > Opret. Navngiv applikationen ollama og indsæt følgende YAML:

version: "3.8"

services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    volumes:
      - /share/Container/ollama:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_KEEP_ALIVE=10m
    networks:
      - ai-network

networks:
  ai-network:
    name: ai-network
    driver: bridge

Skærmbillede: Container Station — Applikationsoprettelsesskærm med YAML-editor
Skærmbillede: Container Station — Indstil hukommelsesgrænsen

Udrul containeren.
Klik på Opret. Container Station vil hente Ollama-billedet og starte containeren. Vent, indtil status viser Kører.
Skærmbillede: Container Station — ollama-container viser "Kører" status
Hent din første model.
Åbn containerens Terminal (eller SSH ind i din NAS og exec din Docker) og kør:
```
# For en let 3B-model (anbefales til første test):
ollama pull llama3.2:3b

# For en standard 9B-model (kræver 16 GB+ RAM):
ollama pull qwen3.5:9b
```
Downloaden kan tage flere minutter afhængigt af din internetforbindelse. En 9B Q4_K_M-model er cirka 4–7 GB.
Note
- Bekræft, at du har tilstrækkelig diskplads, før du henter. Brug ollama list til at kontrollere eksisterende modeller og deres størrelser.
- For ARM-baserede NAS-modeller anbefaler vi at starte med <1B-modellen for at overvåge hukommelsesforbrug.
Test modellen.
Kør i containerens terminal:
```
ollama run qwen3.5:9b
```
Skriv en prompt og bekræft, at du modtager et svar. Skriv /bye for at afslutte.

Metode 2: NVIDIA GPU-accelereret implementering

Note

Yderligere forudsætninger for GPU-tilstand:

NVIDIA GPU installeret og registreret af QTS/QuTS hero
GPU indstillet til Container Station-tilstand i Kontrolpanel
NVIDIA GPU-driver og NvKernelDriver installeret fra App Center

Brug den GPU-aktiverede Docker Compose-konfiguration.

Erstat YAML fra metode 1 med følgende:

version: "3.8"

services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    volumes:
      - /share/Container/ollama:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_KEEP_ALIVE=10m
      - NVIDIA_VISIBLE_DEVICES=all
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - ai-network

networks:
  ai-network:
    name: ai-network
    driver: bridge

Skærmbillede: Container Station — GPU-aktiveret Docker Compose YAML

Note

QNAP's medfølgende NVIDIA-drivere kan være ældre end den nyeste udgivelse. Hvis containeren ikke starter med GPU aktiveret, skal du kontrollere driverversionen med nvidia-smi på værten og sikre, at den er kompatibel med Ollama-billedversionen

Implementer og verificer GPU-adgang.
Efter containeren starter, åbnes dens terminal og kør:
```
nvidia-smi
```
Du bør se din GPU-model, driverversion og hukommelsesinformation.
Træk en model og bekræft GPU-acceleration.
```
ollama pull qwen3.5:9b
ollama run qwen3.5:9b
```
Mens modellen genererer et svar, åbnes en anden terminal og kør nvidia-smi. Du bør observere GPU-hukommelsesbrug og GPU-udnyttelse stige.

Resultat

Efter at have gennemført denne vejledning, vil du have:

Ollama kørende på din QNAP NAS ved http://<NAS-IP>:11434
Modeldata gemt i /share/Container/ollama (overlever container-genopbygninger)
En fungerende LLM tilgængelig via Ollama API

Du kan teste API'en fra enhver enhed på dit lokale netværk:

curl http://<NAS-IP>:11434/api/generate -d '{
  "model": "qwen3.5:9b",
  "prompt": "Hej, hvordan har du det?",
  "stream": false
}'

Vigtigt

OLLAMA_HOST=0.0.0.0-indstillingen eksponerer Ollama API på alle netværksinterfaces. Eksponér ikke port 11434 til internettet. Brug Firewall-regler eller QNAP's netværksindstillinger til at begrænse adgang til kun dit lokale netværk.

Fejlfinding

Containeren afsluttes straks efter start

Dette kan skyldes utilstrækkelig RAM eller GPU-driver mismatch. Tjek containerlogfiler i Container Station. Reducer hukommelsesbegrænsninger eller deaktiver GPU-tilstand.

Modeltrækning fejler midtvejs

Dette kan skyldes utilstrækkelig diskplads eller netværkstidsudløb. Prøv at frigøre Lager-plads. Genkør ollama pull; systemet genoptager fra hvor det stoppede.

Responshastigheden er meget langsom (1–3 tokens per sekund)

Modellen kan køre på CPU i stedet for GPU, eller modellen er for stor til din RAM. Bekræft din GPU-adgang med nvidia-smi inde i containeren. Prøv at bruge en mindre model.

NAS'en bliver uresponsiv under inferens

Dette kan være et "out of memory"-problem: modellen bruger al systemhukommelse. Vi anbefaler at genstarte NAS'en. Sæt en hukommelsesbrugsgrænse i applikationen. Eller brug en mindre model.

"Kan ikke oprette forbindelse til Ollama"-besked fra Open WebUI

Dette kan skyldes en forkert API-URL eller Docker netværksisolering. Du kan bruge http://ollama:11434 hvis du er på samme Docker netværk.

Was this article helpful?

Yes. No.

100% of people think it helps.

For yderligere hjælp kan du spørge andre brugere og QNAP-eksperter i vores community. Gå til QNAP Community

Please tell us how this article can be improved:

The article is missing important information
The article's solutions do not work
The article is too complicated
The article contains incorrect information
The article is out-of-date

If you want to provide additional feedback, please include it below.