# DeepSeek-R1-0528: RAM and VRAM requirements

> DeepSeek-R1-0528 is a 671B DeepSeek-R1 model (Mixture-of-Experts, 37B active per token). At Q4_K_M it needs about **384.1 GB** to run and fits **0 of 40** tracked devices. Minimum to run: high-memory hardware.

Last validated: 2026-08-03. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 377.13 GB | ~384.1 GB |
| Q8_0 | 664.3 GB | ~671.3 GB |
| FP16 | 1348 GB | ~1355 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Apple M1 (8GB)** (8 GB): No, not enough memory
- **iPhone 17** (8 GB): No, not enough memory
- **iPhone 17 Pro** (12 GB): No, not enough memory
- **16GB RAM Laptop (CPU/iGPU only)** (16 GB): No, not enough memory
- **Google Pixel 10 Pro** (16 GB): No, not enough memory
- **Nvidia GeForce RTX 3090 (24GB)** (24 GB): No, not enough memory
- **Apple M4 Pro (48GB)** (48 GB): No, not enough memory
- **Apple M3 Ultra (256GB)** (256 GB): No, not enough memory

Full table of all 40 devices: https://localmodel.run/model/deepseek-r1-0528

## How to run
Quickest path: `ollama run deepseek-r1:671b`. On Mac, LM Studio (ships MLX) is fastest; on Linux, Ollama for chat or vLLM to serve; on Windows, LM Studio or Ollama.

## Details
- Parameters: 671B (MoE, 37B active per token)
- Default context: 160k tokens
- License: MIT (commercial use: yes)
- Released: 2025-05
- HuggingFace: 206,900 downloads/mo, 2457 likes

## FAQ
### How much VRAM or RAM does DeepSeek-R1-0528 need?
About 384.1 GB at Q4_K_M (weights 377.13 GB + KV cache + overhead) at a 4k context. Budget ~671.3 GB for Q8_0.
### Can DeepSeek-R1-0528 run on a laptop?
DeepSeek-R1-0528 is large; you need a high-memory Mac or a 24 GB+ GPU at Q4_K_M.
### Can I use DeepSeek-R1-0528 commercially?
Yes, MIT permits commercial use.

Sources: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528, https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/blob/main/config.json, https://huggingface.co/unsloth/DeepSeek-R1-0528-GGUF/tree/main/Q4_K_M, https://huggingface.co/unsloth/DeepSeek-R1-0528-GGUF/tree/main/Q8_0, https://huggingface.co/unsloth/DeepSeek-R1-0528-GGUF/tree/main/BF16, https://openrouter.ai/deepseek/deepseek-r1-0528, https://ollama.com/library/deepseek-r1:671b, https://aider.chat/docs/leaderboards/
More: https://localmodel.run/model/deepseek-r1-0528