# DeepSeek R1 (0528): hardware requirements
> DeepSeek R1 (0528) (DeepSeek) is a 671B (37B active) mixture-of-experts model with a 128K-token context window, released under the MIT license. It needs about 420GB of memory at Q4_K_M with 8K context.
DeepSeek R1 was the open reasoning model that shook the industry in January 2025, and the May 2025 (0528) update closed much of the gap to the best closed models of the time. DeepSeek's V4 generation has since superseded it with a 1M-token context, a toggleable thinking mode, and far lower memory per token of context. At 671B parameters it needs about 420GB at Q4_K_M with 8K context, so local use means a 512GB Mac Studio, a large multi-GPU server, or a high-memory EPYC system running the experts from RAM. Aggressive 1-bit to 2-bit dynamic quants roughly halve that at a real quality cost.

## Recommended hardware
- **Mac / unified memory:** M3 Ultra 512GB (512GB), Q3_K_M, ~14 tokens/sec

## Memory by quantization
| Quant | Weights | Total @ 8K ctx | Total @ 32K ctx |
| --- | --- | --- | --- |
| Q2_K | 251.6GB | 260.3GB | 262.1GB |
| Q3_K_M | 327.1GB | 338.1GB | 339.8GB |
| Q4_K_M | 406.8GB | 420.2GB | 421.9GB |
| Q5_K_M | 478.1GB | 493.6GB | 495.3GB |
| Q6_K | 553.6GB | 571.4GB | 573.1GB |
| Q8_0 | 712.9GB | 735.5GB | 737.2GB |
| BF16 | 1342.0GB | 1383.4GB | 1385.2GB |

## GPUs that run it fully in memory (fastest first)
| GPU | Memory | Quant | Speed | Price |
| --- | --- | --- | --- | --- |
| M5 Ultra 512GB | 512GB | Q3_K_M | ~21 tok/s | n/a |
| M3 Ultra 512GB | 512GB | Q3_K_M | ~14 tok/s | $9,499 MSRP |

## How to run it
- Ollama: `ollama run deepseek-r1:671b`
- llama.cpp: `llama-server -hf unsloth/DeepSeek-R1-0528-GGUF:Q4_K_M -c 8192 -ngl 99`
- Weights: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528

## Strengths
- Strong step-by-step reasoning, math, and writing
- MLA keeps the KV cache compact (about 69 KiB per token)
- MIT license

## Weaknesses
- Needs about 420GB at Q4_K_M, impractical for most home setups
- Always thinks, often at great length, which is slow at local speeds
- Superseded by DeepSeek V4, which is stronger and cheaper to run
- Text only
Full page: https://llamabuilds.ai/models/deepseek-r1 · Hardware guide: https://llamabuilds.ai/models/deepseek-r1/requirements

---
Source: https://llamabuilds.ai/models/deepseek-r1 · Updated October 14, 2026 · Llama Builds. Speeds marked ~ are estimates from our bandwidth model (https://llamabuilds.ai/methodology); measured results are labeled as such.