On Linux, run ollama serve to start Ollama’s headless HTTP server. For a persistent service, use the documented systemd unit and start it with systemctl. Ollama’s local API uses port 11434; to let another computer connect, configure the service’s OLLAMA_HOST listening address and protect network access with a firewall or reverse proxy.
Choose how to run the server
The right deployment depends on whether you need a temporary foreground process, a service that starts and restarts under Linux, or a containerized environment. The official Ollama documentation covers native Linux installation and systemd, as well as Docker deployments for NVIDIA and AMD GPUs.
| Method | Best fit | What to consider |
|---|---|---|
Foreground ollama serve |
Testing or a manually managed process | Keep the terminal process running; its output is where you inspect logs. |
| Linux systemd service | A persistent Linux host | systemd manages the service lifecycle; customize its environment through a systemd drop-in. |
| Docker | Container isolation or a reproducible deployment | GPU setup varies by vendor, and model storage needs a persistent volume. |
These options do not come with published performance figures in the cited official pages, so choose based on operational requirements rather than an assumed speed advantage. See the Linux installation guide and Docker instructions.
Start Ollama in the foreground
Ollama’s quickstart describes ollama serve as the way to start Ollama without running the desktop application. On a Linux machine where Ollama is installed, open a terminal and run:
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errors#1 Best Overall
- WHY CHOOSE CORE I3-10110U - Better single-core performance: The Core i3-10110U has a higher peak boost clock (4.1 GHz) compared to the Ryzen 3 4300U and the Intel Alder Lake N150 series, making it better for tasks that rely on fast single-core performance (e.g., web browsing, office apps). Better multi-thread performance via Hyper-Threading: the Core i3-10110U offers better performance in multi-threaded workloads compared to the Ryzen 3 4300U, especially for light productivity work and multitasking.
- 16GB RAM MEMORY & 512GB SSD STORAGE - GMKtec Nucbox G3 PRO mini pc is prebuilt with 16GB DDR4 RAM SO-DIMM DUAL CHANNEL, you will enjoy a speedier experience with Built-in 512GB M.2 Hard Drive. Our mini desktop pc boots up in seconds, work on multiple browser tabs, software applications and quickly transfers files. There is a primary slot and secondary expansion storage. Primary slot is M.2 2280 PCIE/SATA and secondary slot is M.2 2242 SATA .
- RICH INTERFACE - Nucbox core i3 mini computer is equipped with USB 3.2*4,up to 5Gbps/S, HDMI(4K@60Hz)×2, 3.5mm Audio Jack. Supports WiFi 6, and Gigabit Ethernet RJ45 2.5GbE network connectivity, Bluetooth 5.2. This Mini PC supports multiple device connection and can be used with servers, monitoring equipment, office equipment, displays, projectors, televisions, etc.
- 4K DUAL SCREEN DISPLAY - Mini desktop computer is equipped with upgraded Intel Graphics(max 1000MHz), supports 4K video playback and AV1 decoding, connect the pc with a projector as a home theatre, enjoy a variety of entertainments. Two HDMI 2.0 ports allows you to multi-task efficiently on two 4K@60Hz displays.
- UPGRADED COOLING FAN - The G3 PLUS has upgraded the cooling fan to reduce fan noise and thermals. We are using an upgraded thermal paste as well to help reduce heat on the CPU.
ollama serveLeave that process running while clients use the server. This is useful for a quick check or a manually managed session; it is not the persistent-service setup described by Ollama for Linux. The terminal displays the foreground process output, which is also the first place to look if startup fails.
Install and run a persistent Linux service
For a durable Linux host, the official guide documents installation with the shell installer and a systemd service. The unit runs as the ollama user and group, uses Restart=always and RestartSec=3, and starts /usr/bin/ollama serve. The guide supplies the service setup; use its current instructions for the full unit contents rather than substituting an undocumented service file.
-
Install Ollama using the documented command:
curl -fsSL https://ollama.com/install.sh | sh -
Reload systemd’s unit definitions and enable the service to start through systemd:
sudo systemctl daemon-reload sudo systemctl enable ollama -
Start it:
sudo systemctl start ollama -
Check its status:
sudo systemctl status ollama
Enabling and starting are separate operations: the documented commands perform each action explicitly. Consult the Ollama Linux guide for the service unit and installation details.
Expose the API to another computer
Ollama’s OLLAMA_HOST setting controls the address on which the service listens. A service configured with OLLAMA_HOST=0.0.0.0 listens on network interfaces rather than only a local interface. This makes remote access possible at the network-listening layer, but it does not by itself provide an access-control boundary. Restrict access with a host firewall or a reverse proxy in a real deployment.
Set the host address for systemd
-
Open a systemd override for Ollama:
sudo systemctl edit ollama -
Add the environment setting under the
[Service]section:[Service] Environment="OLLAMA_HOST=0.0.0.0" -
Reload systemd and restart Ollama so the changed environment takes effect:
sudo systemctl daemon-reload sudo systemctl restart ollama
Use a narrower listening address if your setup calls for it; the official FAQ’s example specifically shows 0.0.0.0. Do not expose the service broadly without deciding how network access will be restricted. The Ollama FAQ documents this environment-setting method.
Free tools Windows power users keep installed
One-click scans. No signup required.
Rank #2
- 12th Intel Alder Lake N95 Processor – The GMKtec G3 S Mini PC is powered by the 12th Gen Intel N95 processor with 4 cores, 4 threads, 6MB cache and a burst frequency up to 3.4GHz. Compared with N100/N5105/N5100/N5095, the N95 delivers up to 36% overall performance improvement. Perfect for routine tasks, office work, and home entertainment, this compact mini desktop is more convenient than traditional bulky PCs.
- 8GB RAM & 256GB SSD Storage – Pre-installed with 8GB DDR4 memory and a fast 256GB M.2 2242 SSD, the G3 S mini desktop offers quicker startup, smoother multitasking, and faster file transfers. Enjoy seamless performance whether you’re working on multiple applications, browsing, or streaming content.
- Rich Interfaces & Connectivity – The G3 S mini computer comes equipped with USB 3.2 (up to 10Gbps), dual HDMI 2.0 (4K@60Hz), and a 3.5mm audio jack. With support for WiFi 5, Bluetooth 5.0, and Gigabit Ethernet (RJ45 1000MbE), it connects easily with monitors, projectors, printers, office equipment, and other peripherals, making it versatile for both home and business use.
- Dual 4K Display Support – Featuring upgraded Intel UHD Graphics (up to 1000MHz), the G3 S supports 4K video playback and AV1 decoding for a smooth viewing experience. With dual HDMI outputs, you can connect two 4K@60Hz displays simultaneously, enabling efficient multitasking for work and entertainment.
- GMKtec WARRANTY - GMKtec offers a 1-year limited GMKtec's warranty for each mini PC, starting from the date of the purchase. All defects due to design and workmanship are covered. With a professional after sales team always ready to attend to your needs, you can simply relax and enjoy your mini PC.
Connect using the documented API port
The documented local API port is 11434. The quickstart shows requests to /api/generate and /api/chat. From another computer, replace localhost with the server’s reachable hostname or address, and ensure the network and host firewall allow the connection to that port.
A minimal generate request, run on the Ollama host, is:
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?"
}'A chat request uses a messages array:
curl http://localhost:11434/api/chat -d '{
"model": "llama3.2",
"messages": [
{"role": "user", "content": "Why is the sky blue?"}
]
}'These examples follow the request shapes in the Ollama quickstart. For a client on another machine, use the server’s reachable address in place of localhost; the exact address depends on your network.
Run Ollama in Docker
The official image is ollama/ollama. The documented GPU commands publish port 11434 and mount a named volume at /root/.ollama, which preserves downloaded models if the container is recreated. NVIDIA and AMD deployments use different runtime and device configuration.
NVIDIA GPU
The documented NVIDIA flow first configures the NVIDIA Container Toolkit and restarts Docker. Then run:
docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollamaAMD GPU
For AMD, the official instructions use the ROCm-tagged image and device mappings:
docker run -d --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama:rocmFollow the vendor-specific setup in the official Docker guide; the NVIDIA flag is not a substitute for the documented AMD device configuration.
Download and run a model in the container
Run the model command inside the running container:
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Rank #3
- ➊ [ Trusted Quality for Everyday Agentic AI ] GEEKOM equips its SSDs with reliable original-grade flash and conducts rigorous stability testing to support dependable everyday operation. This commitment to quality is backed by a 3-year warranty. Simply connect the Air12 to cloud AI services for research, writing, study support and daily productivity—no NPU or complex local setup required. Designed for students, home users, light office work and first-time buyers, the Air12 is a high-value Cloud Agentic PC for everyday tasks
- ➋ [ Intel 7505 processor ] Powered by the Intel 7505 processor (2 cores, 4 threads, up to 3.5GHz), the GEEKOM Mini PC Air12 delivers smooth performance for everyday computing, office tasks, and home entertainment. With enhanced single-core processing, it handles daily workloads efficiently and responsively. Compact, quiet, and energy-efficient — a solid alternative to bulky desktops.
- ➌ [440lbs(200kg) Pressure Rated Metal Frame for Demanding Environments] Unlike the Plastic Shells You’ll Find on Most Mini PCs, geekom Mini Air12 features a triple-reinforced ABS+PC shell, precision-crafted metal frame and baseplate—engineered to withstand up to 440 lbs of pressure for the perfect balance of strength and thermal efficiency. Tool-free upgrades, shock-absorbing feet, and a 3D antenna deliver true durability
- ➍ [Dual-Channel RAM & NVMe SSD Expandability] Ships with 8GB DDR4 RAM and a 256GB NVMe SSD for smooth everyday performance. Dual memory slots and dual storage slots give you the flexibility to upgrade to 64GB RAM and 2TB SSD, so your system can adapt as your workload grows. Enjoy faster load times, smoother multitasking, and long-term reliability.
- ➎ [Triple 4K Displays for Maximum Productivity] Connect up to three 4K monitors via HDMI 2.0, Mini DisplayPort 1.4, and USB-C — ideal for stock trading dashboards, multi-tab research, office document editing, and light spreadsheet work. WiFi 6 and Bluetooth with high-gain antenna ensure stable wireless connections throughout your workspace. 5x USB ports and a full-size SD card reader provide quick access to peripherals and camera files — no adapters required.
docker exec -it ollama ollama run llama3.2The named volume in the run commands keeps downloaded models in /root/.ollama across container recreation. If you omit persistent storage, do not assume models stored only in the container filesystem will survive its replacement.
Use the API beyond generation and chat
The API reference includes endpoints for creating models, listing local models, retrieving model information, copying and deleting models, pulling and pushing models, generating embeddings, listing running models, and retrieving the Ollama version. Use the endpoint reference for request parameters and response formats rather than inferring them from the two basic examples above.
Streaming responses are enabled by default for applicable endpoints. To request a non-streaming response, include "stream": false in the JSON body where supported. Check the API reference for endpoint-specific behavior and the quickstart for basic usage.
Native service or Docker?
Both approaches can run an Ollama API server, but their operational trade-offs differ. Native systemd is the straightforward documented pattern for a persistent Linux service. Docker is useful when isolation or reproducibility matters, but adds container-runtime and device configuration.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
| Decision area | Native Linux with systemd | Docker |
|---|---|---|
| GPU setup | Not detailed as a GPU-specific setup in the cited Linux service instructions. | Vendor-specific: NVIDIA uses --gpus=all; AMD uses the ROCm image and device mappings. |
| Model persistence | Not specified as a separate volume in the cited systemd instructions. | Named volume ollama mounted at /root/.ollama in the documented commands. |
| Service lifecycle | Managed with systemd commands such as enable, start, and status. |
Managed as a container; the documented example runs it detached. |
| Upgrade and rollback | Not stated in the cited service instructions. | Not stated in the cited Docker instructions. |
| Network exposure | Set OLLAMA_HOST through a systemd override; restrict access with a firewall or reverse proxy. |
The documented command maps host port 11434 to container port 11434; apply appropriate network controls. |
| Logs | journalctl for the systemd unit. |
docker logs for the container. |
Logs and troubleshooting
Choose the log source that matches how Ollama was launched. For systemd, follow the unit logs with:
journalctl -u ollama --no-pager --follow --pager-endFor the documented Docker container:
docker logs ollamaFor a manually started ollama serve, inspect the terminal where it is running. Ollama’s troubleshooting guide also advises checking the latest driver and container-runtime setup when GPU discovery fails.
The client cannot connect
-
Check that the server process or service is running. For systemd, inspect
sudo systemctl status ollama; for Docker, inspectdocker logs ollama. -
If connecting remotely to a systemd service, confirm that
OLLAMA_HOSTis set to an address that listens on network interfaces, then reload systemd and restart the service.PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minuteSpecial offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.Rank #4
KAMRUI Pinova P2 Mini PC, AMD Ryzen 7330U(4 Cores, 8 Threads, Up to 4.3GHz), 16GB RAM 256GB SSD, Zen3 Architecture 7nm Processor, 8MB L3 Smart Cache Mini Computers,Triple 4K Display Home/Business- 【AMD Ryzen 7330U】 – The Efficiency-Tuned Powerhouse，AMD Ryzen 7330U (Zen 3, SMT, 4C/8T) in KAMRUI P2 mini PC crushes rivals: Intel i3-10110U (2C/4T, 2019) and N95 (4 efficiency cores, no HT, single-channel memory). Vs predecessor Ryzen 3 4300U (4C/4T): ~50% faster single-core, ~46% multi-core, 8MB L3 cache (vs 4MB). Beats both Intel chips hugely in multi-core, making heavy multitasking, coding, data work smooth at just 15W TDP. High-end power in a cool, efficient box.
- 【AMD Radeon Graphics】– Triple 4K Vision & Fluidity，The integrated Radeon Graphics (based on the modern Vega architecture with 6 CUs) is a visual beast, outclassing the iGPU offerings from both AMD's prior generation and Intel. The Intel UHD Graphics (i3-10110U/N95) struggles with single-channel memory and low execution units, crippling its gaming performance and barely handling basic 4K video without stuttering. While the older Radeon Vega 5 (4300U) was decent, our 7330U's Radeon Graphics (6 CUs) pushes the boundaries, delivering higher graphics clock speeds (up to 1.8GHz) and significantly better rendering capabilities. It can drive triple 4K@60Hz displays with zero lag, edit photos/videos.
- 【Generous Storage & Easy Expansion】The KAMRUI Pinova P2 mini desktop computers comes with 16GB LPDDR4X RAM (higher frequency, lower power) for buttery‑smooth multitasking, and a 256GB M.2 SSD for blazing fast boot‑up, quick file transfers, and no more long loading screens. It also features two storage expansion slots (1x M.2 2280 SATA/NVMe PCIe 3.0 slot + 1x M.2 2280 SATA slot), supporting up to 4TB total (not included). You’ll have all the space you need for projects, media, and important data.
- 【Triple 4K Display Output】The KAMRUI Pinova P2 mini desktop pc is equipped with HDMI 2.0 ×1 + DP 1.4 ×1 + USB 3.2 Gen2 Type‑C ×1 (with DP Alt Mode), enabling simultaneous triple 4K@60Hz output. Whether for home entertainment, remote work, or conference room presentations, it delivers an immersive visual experience. Two USB 3.2 Gen2 Type‑A ports (up to 10Gbps – 21x faster than USB 2.0) make data transfers and device expansion a breeze.
- 【USB 3.2 Gen2 Type‑C: 10Gbps & Versatile Connectivity】The USB 3.2 Gen2 Type‑C port on the KAMRUI P2 small pc supports 10Gbps data transfer speeds and can also output DisplayPort 1.4 video. Together with Gigabit LAN, Wi‑Fi, and Bluetooth, you get a fast, flexible, and productive connected environment – wired or wireless.
-
Check that the client is using the server’s reachable address and port
11434, and that firewall or proxy rules permit the connection.
The service ignores a changed host setting
A systemd environment change needs a systemd reload and service restart. Re-run sudo systemctl daemon-reload and sudo systemctl restart ollama, then inspect status and logs.
The Docker container does not discover the GPU
GPU discovery failures can stem from drivers, the container runtime, or container configuration. Check that the latest driver and the relevant vendor runtime setup are in place, then verify that the run command matches the GPU vendor: NVIDIA’s documented command uses --gpus=all, while AMD’s uses the ROCm image with /dev/kfd and /dev/dri device mappings.
Models are missing after recreating a container
Use persistent storage for /root/.ollama. The documented Docker commands mount the named volume ollama at that path so downloaded models persist across container recreation.
The Tool Desk
Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Or skip the browser setup
If your goal is to capture a screenshot of the running API or a web page about your deployment, ScreenshotNeo is a separate website screenshot API and MCP server; it does not run or expose Ollama. A single GET request can return an image or PDF. The API accepts the other screenshot APIs’ parameter names too.
For example, this cURL request captures a page as WebP; replace the target URL as needed. See the ScreenshotNeo API documentation for available options.
curl -G "https://api.screenshotneo.com/v1/shot" -d access_key=YOUR_API_KEY --data-urlencode url=https://stripe.com -o shot.webp-
Cookie banners are accepted and removed before capture, along with supported consent platforms, newsletter popups, and chat widgets; each cleanup step can be turned off.
-
Bot checks or CAPTCHAs, blank pages, timeouts, failed loads, and cache hits cost nothing; response headers report the page verdict and billing status.
Recommended: Fix Windows Errors and Clear Junk Files in Minutes - Free Scan →Recommended: Crashes or Glitches? A Free Driver Scan Usually Finds the Culprit →Recommended: PC Feels Slow? A Free Scan Shows What's Dragging Windows Down →Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy. -
An MCP server provides
take_screenshot,get_page_info, andcapture_pdftools for Claude, Cursor, and other MCP clients. -
The Free plan includes 1,000 shots per month with no card; paid plans start at $5 for 3,000 shots.
Sign up for ScreenshotNeo’s free plan to try 1,000 screenshots a month with no card.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Recommended Free Tools
