DeepSeek-R1
DeepSeek-R1 is an open-weights language model from DeepSeek, released January 20, 2025. It has 684B parameters (mixture-of-experts, 51B active). The context window is 160K tokens. On the Epoch Capabilities Index it scores 138.6, rank 129 of 256 rated models.
Check it against your own PC →
Can you run DeepSeek-R1 locally?
Even with 32 GB of VRAM and 32 GB of RAM it is too large to run at a usable speed on a single consumer GPU. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Too large | – | – | – | – |
| 8 GB VRAM | Too large | – | – | – | – |
| 12 GB VRAM | Too large | – | – | – | – |
| 16 GB VRAM | Too large | – | – | – | – |
| 24 GB VRAM | Too large | – | – | – | – |
| 32 GB VRAM | Too large | – | – | – | – |
Ready-made quantizations on Hugging Face: unsloth/DeepSeek-R1-GGUF · unsloth/DeepSeek-R1-GGUF-UD · bartowski/DeepSeek-R1-GGUF · calcuis/deepseek-r1 · XythicK/DeepSeek-R1-GGUF · QuixiAI/DeepSeek-R1-AWQ
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 33.9 | MATH level 5, OTIS Mock AIME 2024-2025 |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 93.1% |
| GPQA Diamond | 64.9% |
| Aider Polyglot | 56.9% |
| OTIS Mock AIME | 53.3% |
| Balrog | 34.9% |
| SimpleBench | 17.1% |
Links
Hugging Face: deepseek-ai/DeepSeek-R1 · Epoch AI benchmarks
Models with a similar score
Qwen3-Max · Gemini 2.5 Flash (Sep 2025) · Claude Sonnet 4 · Gemma 4 26B A4B · Mistral Medium 3.5 · Gemini 2.5 Flash (May 2025) · Kimi K2 (Jul 2025) · o1
More from DeepSeek
DeepSeek V4.1 Flash 1017 · DeepSeek V4 Flash Vision Exp · DeepSeek V4.1 Flash · DeepSeek V4 Pro 0813 · DeepSeek V4 Flash 0731 · DeepSeek V4 Pro DSpark · DeepSeek V4 Flash DSpark · DeepSeek-V4-Pro