← Interactive LLM VRAM Calculator — try your own context length & quantization
How much VRAM to run DeepSeek-R1 671B? (FP16/Q8/Q6/Q4 requirements)
Architecture: MoE with 671B total / ~37B active parameters, MLA compressed KV cache (61 layers). Figures are approximations for weights + an 8k-token FP16 KV cache + ~5 GB runtime overhead, based on typical published GGUF sizes. Actual usage varies by runtime and settings.
| Quantization | Weights | Total VRAM (8k context) | Fits on (example) |
|---|---|---|---|
| FP16 full precision (16-bit) | ~1342 GB | ~1348 GB | multi-node GPU cluster (~1.4 TB) |
| Q8_0 8-bit | ~711 GB | ~717 GB | ≥10×A100/H100 80 GB or 4×MI300X 192 GB |
| Q6_K ~6.6-bit | ~550 GB | ~556 GB | 8×A100/H100 80 GB (640 GB) |
| Q5_K_M ~5.7-bit | ~476 GB | ~482 GB | 8×A100 80 GB or Mac Studio 512 GB |
| Q4_K_M ~4.8-bit | ~404 GB | ~410 GB | 6×A100/H100 80 GB or Mac Studio 512 GB |
How much VRAM do I need to run DeepSeek-R1 671B?
You need roughly ~410 GB of GPU or unified memory to run DeepSeek-R1 671B at Q4_K_M — for example 6×A100/H100 80 GB or a Mac Studio with 512 GB of unified memory. At its native FP8 precision the weights alone are ~713 GB. The full DeepSeek-R1 is a 671B-parameter MoE model: only ~37B parameters are active per token, but ALL 671B must be loaded in memory. Its MLA attention keeps the KV cache small (well under 1 GB at 8k), but the weights alone put it firmly in multi-GPU-server or 512 GB-unified-memory territory. Note the original release is FP8 (~713 GB), so the FP16 row is a theoretical conversion.
What affects these numbers?
Three things: the quantization (bytes per parameter), the KV cache (grows linearly with context length — the table assumes 8k tokens), and runtime overhead. Longer contexts need more memory; quantizing the KV cache (e.g. q8_0 cache in llama.cpp) roughly halves that part. Use the interactive calculator to plug in your exact context length and quantization.