LLMs · DeepSeek
DeepSeek R1 0528 (671B)
- Parameters
- 685B (37.0B active)
- Architecture
- Mixture of experts
- Max context
- 160K tokens
- License
- mit
- Released
- 2025-05
How to run it
Quickest · Ollama
One command downloads a ready-to-run version and starts a chat.
ollama run deepseek-r1:671bQuantized files · GGUF
Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.
huggingface.co/unsloth/DeepSeek-R1-0528-GGUF (opens in a new tab)
ollama run hf.co/unsloth/DeepSeek-R1-0528-GGUFOriginal weights · Hugging Face
Full-precision files from DeepSeek, for fine-tuning, vLLM, Transformers.
huggingface.co/deepseek-ai/DeepSeek-R1-0528 (opens in a new tab)
Official repo · GitHub
Reference code, inference scripts and docs from DeepSeek. The weights themselves download from Hugging Face.
github.com/deepseek-ai/DeepSeek-R1 (opens in a new tab)
git clone https://github.com/deepseek-ai/DeepSeek-R1Memory needed
Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.
| Quantization | Quality | Weights | Total at 8K context | Total at 32K context | Download |
|---|---|---|---|---|---|
Q2_K |
Low | 274 GB | 275 GB | 277 GB | GGUF · folder (opens in a new tab) |
Q3_K_M |
Low | 335 GB | 337 GB | 338 GB | GGUF · folder (opens in a new tab) |
Q4_K_M |
Good | 418 GB | 419 GB | 420 GB | GGUF · folder (opens in a new tab) |
Q5_K_M |
High | 486 GB | 487 GB | 489 GB | GGUF · folder (opens in a new tab) |
Q6_K |
High | 561 GB | 562 GB | 564 GB | GGUF · folder (opens in a new tab) |
Q8_0 |
Very high | 726 GB | 727 GB | 729 GB | GGUF · folder (opens in a new tab) |
F16 |
Full | 1,369 GB | 1,370 GB | 1,372 GB | GGUF · folder (opens in a new tab) Original weights (opens in a new tab) |
Best hardware for DeepSeek R1 0528 (671B)
| Grade · points | Hardware | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 83 ptsGreat (A) · 83 of 100 points: Model quality 35.2/45, Memory fit 24.0/25, Speed 9.2/15, Memory use 15.0/15 | Apple M3 Ultra (512 GB) | Q3_K_M | 367 GB / 384 GB | 15.1 tok/s | Tight fit |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.