08/02/2025 7:01 am
Topic starter
I'm looking to run the full DeepSeek R1 model and want to know what the best GPU options are. I've heard that the model requires a significant amount of memory, possibly over 400GB, which seems out of reach for most consumer GPUs. Are there specific GPUs that can handle this model effectively? Additionally, what are the performance differences between using the full model versus distilled versions? Any recommendations or experiences would be greatly appreciated!
Model Variant | Parameters (B) | VRAM (GB) | GPU | CPU | RAM (GB) |
---|---|---|---|---|---|
DeepSeek-R1 | 671 | ~1,342 | NVIDIA A100 80GB ×16 | AMD EPYC 9654 / Intel Xeon Platinum 8490H | 2,048+ |
DeepSeek-R1-Distill-Qwen-1.5B | 1.5 | ~0.7 | NVIDIA RTX 3060 12GB+ | AMD Ryzen 7 5800X / Intel i7-12700K | 16+ |
DeepSeek-R1-Distill-Qwen-7B | 7 | ~3.3 | NVIDIA RTX 3070 8GB+ | AMD Ryzen 9 5900X / Intel i9-12900K | 32+ |
DeepSeek-R1-Distill-Llama-8B | 8 | ~3.7 | NVIDIA RTX 3070 8GB+ | AMD Ryzen 9 5950X / Intel i9-13900K | 32+ |
DeepSeek-R1-Distill-Qwen-14B | 14 | ~6.5 | NVIDIA RTX 3080 10GB+ | AMD Ryzen 9 7900X / Intel i9-13900K | 64+ |
DeepSeek-R1-Distill-Qwen-32B | 32 | ~14.9 | NVIDIA RTX 4090 24GB | AMD Threadripper 7980X / Intel Xeon W9-3495X | 128+ |
DeepSeek-R1-Distill-Llama-70B | 70 | ~32.7 | NVIDIA RTX 4090 24GB ×2 | AMD EPYC 9654 / Intel Xeon Platinum 8490H | 256+ |
I use the new released RTX 5090 for DeepSeek-R1-Distill-Qwen-32B, works well, no problems.
My laptop with RTX 4090 can run 32b.