β All modelsMODEL FAMILY
DeepSeek R1 β every size compared
DeepSeek's DeepSeek R1 family spans 6 models from 1.8B to 70.6B parameters. The smallest needs just 3 GB of RAM; the largest wants 64 GB.
All DeepSeek R1 models
| Model | Params | Download (Q4) | Min RAM | Context window | Best for |
|---|---|---|---|---|---|
| DeepSeek R1 1.5B | 1.8B | 1.1 GB | 3 GB | 128K | Reasoning |
| DeepSeek R1 7B | 7.6B | 4.6 GB | 8 GB | 128K | Reasoning |
| DeepSeek R1 8B | 8B | 4.9 GB | 8 GB | 128K | Reasoning |
| DeepSeek R1 14B | 14.8B | 9.0 GB | 16 GB | 128K | Reasoning |
| DeepSeek R1 32B | 32.8B | 19.9 GB | 32 GB | 128K | Reasoning |
| DeepSeek R1 70B | 70.6B | 42.8 GB | 64 GB | 128K | Reasoning |
Sizes are 4-bit (Q4_K_M) GGUF builds β the standard for running models locally. Β· Data updated: 2026-06-11 Β· How we calculate these numbers β
Which DeepSeek R1 should you pick?
Take the largest one your memory allows β bigger versions of the same family are almost always better at the same quantization. Click any model for full requirements and a live check on your machine.