Free tools Windows power users keep installed
One-click scans. No signup required.
You can run a distilled DeepSeek-R1 model locally with Ollama on a regular computer, but the right model depends on your available memory, storage, and tolerance for slower responses. Start with a small distilled tag such as 7B; the full 671B-parameter DeepSeek-R1 model is a server-scale workload, not a typical desktop install.
Which DeepSeek model can you run locally?
DeepSeek-R1 is a model family, not one download. DeepSeek publishes a full 671B-parameter model and smaller distilled models from 1.5B to 70B. The distilled models are the practical starting point for personal computers. DeepSeek lists the full model as 671B total parameters and 37B activated parameters; “37B activated” does not mean that only 37B of weights must be stored in memory. For the full model’s deployment footprint, use the serving requirements in the vLLM recipe rather than the activated-parameter figure. DeepSeek’s model repository
As an Amazon Associate I earn from qualifying purchases.
Ollama’s library lists these tags and download sizes. They are artifact sizes, not estimates of the RAM or GPU memory needed to run each model.
| Ollama tag | Listed artifact size | Practical orientation |
|---|---|---|
| 1.5B | 1.1GB | Smallest listed option; a reasonable place to begin on limited hardware. |
| 7B | 4.7GB | A modest first choice; used in the quick-start command below. |
| 8B | 5.2GB | Currently the library’s default when you run the unqualified model name. |
| 14B | 9.0GB | A larger distilled option; check actual memory use and speed on your machine. |
| 32B | 20GB | A substantial local workload; a configurable inference server may suit advanced setups. |
| 70B | 43GB | A large model that can exceed the practical memory capacity of many personal systems. |
| 671B | 404GB | Full-model quantized tag; not a casual desktop download. |
Ollama also lists an FP16 full-model tag at 1.3TB. These figures are published by the Ollama model library; they describe files, not a universal hardware minimum. Your runtime’s memory use also depends on weight format, context length, inference engine, and configuration. The available official figures do not establish a complete RAM and VRAM minimum for every computer.
#1 Best Overall
- [Personal AI Supercomputer]: Built for AI developers, researchers, data scientists, startup labs, and university labs, the ASUS Ascent GX10 is designed for local AI development, model testing, inferencing, RAG workflows, and agentic AI experimentation beyond a standard mini PC.
- [NVIDIA GB10 Grace Blackwell Superchip]: Powered by the NVIDIA GB10 Grace Blackwell Superchip with Blackwell GPU architecture and a 20-core Arm CPU, GX10 delivers up to 1 PetaFLOP of FP4 AI performance for generative AI prototyping and local model workflows.
- [128GB Unified Memory for Large AI Workloads]: 128GB LPDDR5x unified memory helps support demanding AI development and testing scenarios, including workflows for large language models, multimodal AI, local inference, fine-tuning experiments, and model evaluation.
- [2TB NVMe Storage for AI Projects]: The 2TB M.2 2242 NVMe SSD provides high-speed local storage for AI model libraries, datasets, Docker containers, checkpoints, development environments, and RAG or vector database workflows.
- [DGX OS and Advanced Connectivity]: DGX OS and the NVIDIA AI software stack help streamline CUDA, PyTorch, TensorFlow, TensorRT, NVIDIA NIM, and AI Blueprint workflows, while Wi-Fi 7, 10GbE, USB-C, HDMI, and NVIDIA ConnectX-7 support modern lab and desktop deployments.
What hardware do you need?
Memory and graphics
Choose the smallest distilled tag that meets your needs, then try a larger one only if the computer can load it and the response speed is acceptable. A model file can be smaller than the total memory needed during inference. GPU acceleration may help when supported by your runtime and hardware, but the cited model listings do not specify consumer GPU minimums or guarantee a particular speed. A single VRAM number would therefore be misleading.
DeepSeek’s repository lists a 128K context length for the full R1 model. Ollama advertises 128K context for its smaller tags and 160K for the 671B tag. These are published context-window figures, not promises that every machine can practically use the maximum: usable context and concurrent requests depend on runtime settings and available memory.
Rank #2
- Built for Local AI and Advanced Workflows – The BOSGAME M5 AI Mini PC is powered by AMD Ryzen AI Max+ 395 with 16 cores, 32 threads, up to 5.1GHz, 50 TOPS NPU performance and up to 126 TOPS total AI performance. It is designed for local AI inference, private AI assistants, coding, data analysis, virtualization, content creation and demanding multitasking while keeping sensitive data on the device.
- 128GB Unified Memory for Large Models and Creative Projects – M5 includes 128GB LPDDR5X-8000 unified memory, giving the CPU and Radeon 8060S graphics access to a large shared memory pool. This helps support memory-intensive AI workloads, large project files, multiple virtual machines, 3D work, video editing and complex professional applications without the capacity limits of typical 32GB or 64GB mini computers.
- Radeon 8060S Graphics for Creation, Rendering and Gaming – Integrated Radeon 8060S graphics with 40 RDNA 3.5 compute units delivers high-end visual performance without a separate graphics card. Use the M5 creator workstation for 4K video editing, 3D rendering, CAD, AI image workflows, high-resolution media and modern gaming, while maintaining a compact desktop footprint.
- 2TB PCIe 4.0 SSD and Flexible Expansion – A pre-installed 2TB NVMe PCIe 4.0 SSD provides fast access to models, datasets, media libraries and project files. A second M.2 2280 PCIe 4.0 slot allows additional storage expansion, while the SD 4.0 card reader supports efficient photo and video workflows for creators and production teams.
- Professional Connectivity and Four-Display Support – Dual USB4 ports, HDMI 2.1 and DisplayPort 1.4 support up to four displays and resolutions up to 8K@60Hz. WiFi 7, Bluetooth 5.4 and 2.5GbE deliver fast networking for cloud collaboration, NAS access and business deployment. Windows 11 Pro, performance-mode switching, Wake-on-LAN and auto power-on support flexible workstation use.
Storage
Allow space for the model files as well as the operating system and runtime. The listed artifacts range from 1.1GB for 1.5B to 404GB for the 671B quantized tag; the library’s FP16 full-model tag is 1.3TB. If you plan to keep several models, budget for their combined downloads. The cited sources do not establish a minimum drive speed or show that an NVMe SSD is required.
Recommended Free Tools
The full 671B model is a different class of deployment
The current vLLM DeepSeek-R1 deployment recipe gives an FP8 configuration with 805GB minimum VRAM and recommends eight H200 GPUs. It also describes an FP4 NVIDIA configuration for four B200 GPUs. These are specific serving recipes for large-scale hardware, not consumer-PC recommendations. DeepSeek directs users seeking to run the full R1 locally to its DeepSeek-V3 repository.
Rank #3
- 【High-Performance APU】The MS-S1 MAX features an AMD Ryzen AI Max+ 395 APU, integrating a Zen 5 architecture CPU (up to 5.1GHz, 16C/32T, 64M L3 Cache), an RDNA 3.5 GPU, and an NPU (50 TOPS). The total system output is 126 TOPS. It provides powerful parallel computing capabilities for demanding AI workflows. It is ideal for running local LLMs, multimodal models, and computationally intensive tasks
- 【128GB UMA Memory】Equipped with up to 128GB of LPDDR5x-8000MT/s unified memory, it enables the CPU and GPU to access a shared, high-bandwidth memory pool with extremely low latency. Ideal for large-scale AI inference, 3D workloads, and complex timelines in video editing. It eliminates traditional VRAM bottlenecks, ensuring smoother data transfer during high-intensity computations. The UMA design maximizes performance stability under high loads
- 【Flexible Expansion】The MS-S1 MAX features USB4 V2 (up to 80Gbps), dual 10GbE LAN, HDMI 2.1 (up to 8K60), a full-length PCIe x16 expansion slot, and dual M.2 slots supporting up to 16TB RAID 0/1. Wi-Fi 7 provides stronger signal coverage and a more stable wireless experience. The slide-out design facilitates upgrades and maintenance. It easily adapts to personal, studio, or rack-mount enterprise environments
- 【High-Efficiency Cooling System】Utilizing an aerospace-grade aluminum alloy chassis, copper base plate, six heat pipes, dual turbine fans, and advanced PCM thermal conductive material, it maintains stable cooling performance even under continuous load. This system supports 130W continuous power and 160W peak power operation, with a built-in 320W power supply. It boasts multiple global certifications including CCC, FCC, UL, CE, and UKCA, ensuring stable and reliable operation in various environments
- 【Cluster Design】Two MS-S1 MAX units can be configured as a dual-unit cluster to run a large 235B Q4 model locally, achieving an output speed of 10.87 tok/s. Supporting 2U rack deployment, multiple MS-S1 MAX units can be cascaded into a distributed cluster to create a high-efficiency AI computing center. A cluster of four MS-S1 MAX units successfully ran a DeepSeek-R1 671B Q4 large model. A reserved cluster power-on interface allows for unified start-up and shutdown
Run a distilled model with Ollama
Ollama is a straightforward route for trying a model locally. Install Ollama using its current instructions for your operating system, then run a model by specifying its tag. Using an explicit size makes the choice reproducible; the bare command currently selects the 8B default.
- Install Ollama from its official download and setup instructions.
- Open a terminal and run
ollama run deepseek-r1:7b. To try another listed size, substitute a tag such as14bor32b. - Wait for the model download to finish, then enter a prompt in the chat session.
The library documents a local HTTP chat API as well as the command-line route. Check Ollama’s current documentation for API use and configuration details. The model library and tags can change, so confirm the selected tag there if a command no longer resolves.
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.
Use vLLM or SGLang for a configurable server
If you need a serving stack rather than a simple local chat, DeepSeek says its distilled models can be used like Qwen or Llama models. Its repository includes a vLLM example for deepseek-ai/DeepSeek-R1-Distill-Qwen-32B with tensor parallelism set to two and a maximum model length of 32K; it also names SGLang as an option. Follow the selected runtime’s current installation steps and flags, since requirements can change. The example is a configuration reference, not evidence that every two-GPU system can serve that model comfortably.
How to choose a starting size
- Limited storage or memory: Begin with 1.5B or 7B and assess how responsive it is for your tasks.
- Room for a larger distilled model: Try 14B or above only after checking whether your runtime can load it with acceptable performance.
- Need a configurable service: Consider vLLM or SGLang for distilled weights, following the runtime’s current configuration guidance.
- Need the full 671B checkpoint: Plan for server-class multi-GPU infrastructure; the published vLLM recipe is not a home-PC setup.
DeepSeek’s repository advises: “NOTE: Before running DeepSeek-R1 series models locally, we kindly recommend reviewing the Usage Recommendation section.” Read that guidance in the official repository before using the models.
Quick Recap
Best Value
- 【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 128GB 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.
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.
