Ollama gives you a command-line workflow and a local REST API for downloading, running, inspecting, customizing, and removing language models. Start with ollama run to try a model; use ollama list and ollama ps to see what is stored and running. Your computer’s memory and the model’s size will shape what is practical.
Install Ollama for your operating system
Use the current instructions for your platform: Ollama’s official quickstart links to macOS and Windows downloads, Linux installation options, and the official Docker image. Linux’s quickstart includes this shell installer command:
curl -fsSL https://ollama.com/install.sh | shLinux users who need more control can follow the separate manual instructions linked from the quickstart. The project documentation index also links platform-specific and Docker guides; use those rather than assuming one installation method fits every system: Ollama documentation index.
Choose a model that fits your machine
Model names may include tags or variants, and the available library changes over time. Browse the Ollama model library and check the selected model’s current requirements before downloading it.
Recommended Free Tools
#1 Best Overall
- EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 128GB pool, which is perfect for running LLMs such as Deepseek 70B Q8, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 12% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
Ollama’s quickstart gives the following example artifact sizes and minimum RAM guidance. Artifact size is the download size shown for these examples; it is not the same as the RAM needed to run a model.
| Quickstart example | Example artifact size | Quickstart RAM guidance |
|---|---|---|
| Llama 3.2 1B | 1.3 GB | not stated for this specific example; the quickstart gives at least 8 GB for its 7B examples |
| Llama 3.2 3B | 2.0 GB | not stated for this specific example; the quickstart gives at least 8 GB for its 7B examples |
| 7B model examples | not stated | at least 8 GB |
| 13B model examples | not stated | at least 16 GB |
| 33B model examples | not stated | at least 32 GB |
| Llama 3.1 70B | 40 GB | not stated for this specific example |
| Llama 3.2 Vision 90B | not stated | not stated |
| Llama 3.1 405B | 231 GB | not stated for this specific example |
These sizes and RAM figures are examples from the Ollama quickstart, whose retrieved page does not state a publication year. The RAM figures are guidance, not guarantees of speed or suitability: model variant, quantization, context length, and device can all affect actual use. A large download size also does not by itself establish the memory required at runtime.
Download and run a model
To download and start the quickstart’s basic example, open a terminal and run:
ollama run llama3.2Ollama downloads the model if it is not already present, then starts an interactive session. For an explicit download or update without immediately opening a chat, use:
Free tools Windows power users keep installed
One-click scans. No signup required.
Rank #2
- Built for Local AI Development: AMD Ryzen AI Halo is designed for local AI development and inference, featuring 128GB unified memory and support for up to 200B parameter models to build and run intensive AI workloads locally.
- 128GB Unified Memory: Features 128GB LPDDR5x unified memory at 8000 MT/s with 256 GB/s memory bandwidth, providing a shared memory pool across the CPU, GPU, and NPU to support larger AI models.
- AMD Ryzen AI Max+ 395 Processor: Features 16 cores, 32 threads, and Zen 5 architecture, paired with AMD Radeon 8060S integrated graphics featuring 40 RDNA 3.5 compute units and an AMD XDNA 2 NPU with up to 50 TOPS.
- Linux AI Developer Platform: Purpose-built for Linux-based AI development with full AMD ROCm software support and preloaded tools, models, and workflows optimized for local AI development.
- Compact, Connected Design: Includes a 2TB M.2 SSD, 10GbE LAN, Wi-Fi 7, Bluetooth 5.4, USB-C connectivity, and HDMI 2.1b.
ollama pull llama3.2A pull can update an existing local copy, downloading only the difference. Model names and tags are subject to change, so use the library’s current listing for the exact identifier you want.
Inspect and manage local models
These commands answer different questions: list shows stored models, while ps shows models currently loaded.
| What you want to do | Command |
|---|---|
| List models stored locally | ollama list |
| See models currently loaded | ollama ps |
| View information about a model | ollama show <model> |
| Stop a running model | ollama stop <model> |
| Remove a local model | ollama rm <model> |
| Copy a model under another name | ollama cp <source> <destination> |
Replace each angle-bracketed value with the model name or source and destination names you intend to use. Removing a model deletes that local copy; pull it again if you later want to use it.
Customize a model with a Modelfile
A Modelfile can point to a library model or a local GGUF file and specify supported customization, such as a parameter or system message. This example starts from a library model:
Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Scan for outdated or missing drivers - takes under a minute3Repair Windows errors before they cause bigger problemsRank #3
- EVOLUTION AMD RYZEN AI MAX+ 395 MINI PC - GMKtec EVO-X2 is the next evolution in AI mini PC Ryzen Strix Halo series. Thanks to AMD Simultaneous Multithreading (SMT) the core-count is effectively doubled, to 32 threads. Ryzen AI Max+ 395 has 64 MB of L3 cache and can boost up to 5.1 GHz, depending on the workload. The Ryzen AI Max+ 395 is currently rated as the "most powerful x86 APU" on the market for AI computing.
- AI NPU with XDNA 2 ARCHITECTURE - Powered by 16 “Zen 5” CPU cores, 50+ peak AI TOPS XDNA 2 NPU and a truly massive integrated GPU driven by 40 AMD RDNA 3.5 CUs, the Ryzen AI MAX+ 395 is a transformative upgrade and delivers a significant performance boost over the competition. The Ryzen AI Max+ 395 excels in consumer AI workloads like the llama.cpp-powered application: LM Studio. Shaping up to be the must-have app for client LLM workloads, LM Studio allows users to locally run the latest language model without any technical knowledge required and unleash their creativity and productivity.
- AMD RADEON 8090S iGPU GAMING PC - The AMD Radeon RX 8060S offers all 40 CUs with up to 2.9 GHz graphics clock and uses the new RDNA 3.5 architecture. The powerful iGPU is positioned between an RTX 4060 and 4070 laptop GPU and therefore enables gaming in FHD at maximum details in most demanding games. The 8060S can also utilize the full 64GB pool, which is perfect for running LLMs such as Deepseek 32B, which runs comfortably on this machine.
- EIGHT CHANNEL LPDDR5X - LPDDR5X is a new ground breaking memory small form factor installed on-board. With blazing speeds up to to 8000MT/s, it runs 1.5x faster than the DDR5 SODIMMs; 90% better performance over DDR5 SODIMMs in video conferencing and photo editing; 30% better performance in productivity apps; 4% better performance in digital content workloads.
- QUAD SCREEN 8K DISPLAY SUPPORT - EVO-X2 AI Mini PC support 4-screen 4K/8K output via HDMI 2.1 (8K@60Hz), DisplayPort 1.4 (4K@60Hz), and dual USB 4 40Gbps Transfer speed (supporting PD3.0/DP1.4/DATA). Ideal for gaming, video editing, and multitasking, it provides expansive and crisp multi-display support.
FROM llama3.2
PARAMETER temperature 0.7
SYSTEM "You are a concise writing assistant."
Save it as Modelfile, then build and run the named model:
ollama create writing-assistant -f Modelfile
ollama run writing-assistantTo import a local GGUF file instead, set the FROM line to its path, for example:
FROM ./model.ggufThen create and run it with the same commands, substituting your desired model name. These examples cover a basic workflow, not every supported format or directive. Check the current Modelfile reference and importing models guide for supported syntax and formats.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Call Ollama’s local REST API
Ollama’s quickstart demonstrates a local API on port 11434. If you need to start the service without the desktop application, run:
Crashes, 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 minuteWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstallRank #4
- 【Leading AI Mini Workstation】MINISFORUM AI MS-S1 Max Workstation comes with AMD Ryzen AI Max+ 395 processor, which uses AMD's latest generation Zen 5 architecture. It has 16 Cores and 32 Threads, the boost clock is up to 5.1GHz. The overall processor performance is up to 126 TOPS, and the NPU performance reaches up to 50 TOPS. AMD Ryzen AI enables improved productivity, advanced collaboration, and improved efficiency.
- 【AMD Radeon 8060S Graphics 】The MS-S1 Max Mini PC equipped with AMD Radeon 8060S Graphics which built on the new generation of RDNA 3.5 architecture AMD graphics, it brings ultra-high frame rate experiences and advanced content creation features anywhere and delivers staggering performance. It can handle all your computing and multimedia tasks efficiently.
- 【Five 8K Video Output】This MS-S1 Max Workstation comes with five video outputs, 1x HDMI (8K@60Hz), 2x USB4(40Gbps,Alt DP2.0,PD out 15W) and 2x USB4 V2(80Gbps,Alt DP2.0,PD out 15W) Outputs, which support multiple monitors display at the same time and provide a larger and wider filed of view and improve your work efficiency. It is used in fields that require high-performance computing and graphics processing, including digital signage and securities trading, as well as work that uses CAD, such as engineering design, scientific calculations, animation production, and post-production for movies and television
- 【 Fast and Stable Wire & Wireless Speed】It comes with Two 10G Lan Ports for wired connection and and Wi-Fi 7 / BT5.4 for wireless connection, which increased the network speed greatly and expand its functions and improved performance of computer to a large extent and allows you to use more networks such as software routers (OpenWRT / DD-WRT / Tomato etc.), firewalls, NAT, network isolation etc.
- 【Large Storage & Flexible Expandability】This Workstation equipped with 64GB LPDDR5-8000MHz + 2TB M.2 2280 PCIe4.0 SSD. There is another PCIe4.0 SSD slot available for up to 8TB, these SSD slots are compatible with RAID0 and RAID1, you can store movies, videos, photos, important files easily. What’s more, it also comes with 1x standard PCIex16 slot(PCIe4.0x4) inside.
ollama serveIn another terminal, send a generation request with curl:
curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?"
}'For a chat-style request, use the messages array at /api/chat:
curl http://localhost:11434/api/chat -d '{
"model": "llama3.2",
"messages": [
{"role": "user", "content": "Why is the sky blue?"}
]
}'These are basic quickstart examples. For request options, response behavior, and other endpoints, consult the current API reference. The documentation index also links an OpenAI-compatibility reference for applications built around that interface.
Pick an interface or integration by where you want to work
The official quickstart lists community integrations, but it does not rank them or establish that one is best. Use the list as a directory and choose according to your workflow:
- Terminal: Use the Ollama CLI when you want direct commands and a lightweight interaction.
- Desktop or web chat: Look for a community client that provides the interface you prefer, and check whether inference remains on your machine or is routed to a cloud deployment.
- Your own application: Use the local REST API when you want an app to send prompts to Ollama; verify the client’s supported API format and the current endpoint documentation.
Ollama’s quickstart integration directory is the starting point for community options; inclusion there is not an endorsement or performance comparison.
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.
