Free tools Windows power users keep installed
One-click scans. No signup required.
You can run a DeepSeek model on your computer with Ollama: install the app, choose a model tag such as deepseek-r1:7b, and run it from a terminal. Start with a distilled R1 model rather than the full 671B-parameter checkpoint. The download size helps estimate disk space, but it does not tell you how much memory or compute the model needs while answering.
How do I run DeepSeek locally?
For a first experiment, use Ollama with a smaller DeepSeek-R1 distilled model. Ollama documents a direct command for its default R1 tag and size-specific tags for choosing a variant. Install Ollama using its official download page, then check that the current Ollama version supports your operating system and the model you intend to run.
As an Amazon Associate I earn from qualifying purchases.
- Choose a model size that fits your available disk space and is plausible for your computer’s memory and compute. The download figures below are file sizes, not minimum hardware specifications.
- Open a terminal and run the command for the chosen tag. For example, use
ollama run deepseek-r1:7borollama run deepseek-r1:8b. To use the default tag instead, Ollama documentsollama run deepseek-r1. - Wait for the model files to download and for Ollama to start the model. When it is ready, enter a short prompt in the terminal.
- If it will not load or is too slow for practical use, try a smaller model. Runtime options such as quantization may also help, but select a configuration supported by your runtime rather than assuming a particular setting will work on every machine.
The Ollama library lists model tags and download sizes on its DeepSeek-R1 model page. Its page documents the model commands; it does not provide a universal installer walkthrough or a single RAM or VRAM minimum for all computers.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Which DeepSeek model should I download?
DeepSeek’s R1 repository lists distilled models at several sizes, as well as the full R1 checkpoint. The smaller distilled variants are the practical place to start on a personal computer; full-scale R1 and V3 are in a different deployment class.
#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 R1 model size | Listed download size | How to interpret it |
|---|---|---|
| 1.5B | 1.1 GB | Smallest listed option; a more conservative first trial, not a guarantee of acceptable speed or fit. |
| 7B | 4.7 GB | Ollama documents the tag deepseek-r1:7b. |
| 8B | 5.2 GB | Ollama documents the tag deepseek-r1:8b. |
| 14B | 9.0 GB | Larger download than 7B or 8B; check runtime demands before choosing it. |
| 32B | 20 GB | Substantial storage and runtime demands; not a default choice for an unknown computer. |
| 70B | 43 GB | Large model for a local setup; verify the intended runtime and hardware first. |
| 671B | 404 GB | Full-scale R1, not a typical one-computer beginner download. |
The listed figures are Ollama’s model file sizes, accessed in 2026; they are not promises about load time, usable context, response speed, or the memory needed to run inference. DeepSeek’s R1 repository identifies the distilled variants and the 671B full model.
Can I run DeepSeek on my PC without a GPU?
The sources do not establish a universal minimum RAM or VRAM for every model, quantization, context length, batch size, and runtime. A GPU is not a safe all-purpose requirement or guarantee: whether a particular model runs acceptably on a CPU-only computer depends on the exact setup. Check the current guidance for your runtime and model configuration, and begin with a smaller variant if you are experimenting on an unspecified PC.
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.
Why download size is not a memory requirement
A downloaded model file occupies disk storage. During inference, memory use also depends on factors including model precision or quantization, context length, batch size, runtime overhead, and whether weights are split across devices. DeepSeek’s older DeepSeek-LLM documentation illustrates how much the configuration matters: its 7B profile on one A100 40 GB reports peak usage from 13.29 GB at batch size 1 and sequence length 256 to 21.25 GB at sequence length 4096. Those are measurements for that specific older profile, not requirements for a current consumer PC or an Ollama R1 model. The same documentation’s 67B profile used eight A100 40 GB GPUs. See the DeepSeek-LLM repository for that configuration.
Recommended Free Tools
Plan disk space separately
Use the listed download size to plan storage, and allow for other files and applications on the same drive. If internal space is limited, an external SSD can provide room for model files, but storage does not replace the memory or compute needed to run them.
Rank #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.
What changes with full DeepSeek-R1 or V3?
The official full R1 and V3 checkpoints are 671B-parameter models. DeepSeek describes V3 as having 671B total parameters and 37B activated parameters; the activated-parameter figure does not make the full model a small download or a routine single-computer setup. For large-model deployment, DeepSeek’s V3 repository lists frameworks including DeepSeek-Infer, SGLang, LMDeploy, TensorRT-LLM, vLLM, and LightLLM, plus hardware paths for AMD GPUs through SGLang and for Huawei Ascend. Support, compatible hardware, precision options, and launch steps are version-sensitive; consult the current documentation for the framework and hardware you plan to use.
DeepSeek’s V3 repository describes tensor and pipeline parallelism across devices and network-connected machines. Its own demo instructions show two nodes with eight processes per node, alongside model download and conversion steps. That is a distributed deployment example, not a beginner command for running V3 on one ordinary computer.
Rank #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.
Platform notes for the official V3 demo
The V3 repository’s included demo specifies Linux and Python 3.10. It also says, in the context of that demo, “Hugging Face’s Transformers has not been directly supported yet.” This is not a blanket statement about every community implementation or other runtime. The demo’s platform and software requirements should not be applied to every framework listed by DeepSeek.
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 problemsQuick 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.
