LLM RAM Calculator → Hardware Guides

How Much VRAM to Run DeepSeek R1?

DeepSeek R1 is a 671B MoE model. At FP16, it requires ~670GB VRAM — a 8× H100 cluster. For most users, run the distilled variants: R1 Distill Qwen 32B (fits in 24GB at Q4) or R1 Distill Llama 70B (fits in 44GB at Q4). Full R1 via API is $0.55/M input — cheaper than self-hosting at most scales.

VRAM requirements by quantization level

QuantizationVRAM neededQualityFits on
FP16 (full)670GBFull quality8× H100 80GB · 16× A100 80GB
Q4 (full)380GBGood5× H100 80GB · 8× A100 80GB
R1 Distill Qwen 32B (Q4)22GBStrong (distilled)RTX 4090 · RTX 5090 · A100 40GB
R1 Distill Llama 70B (Q4)44GBExcellent (distilled)A100 80GB · H100 PCIe

GPU recommendations & rental prices

RTX 4090 (for Distill 32B)
Practical choice for distilled R1 — $0.69/hr on RunPod.
$0.69/hr
spot avg
A100 80GB (for Distill 70B)
Best quality distilled option — fits Q4 in one GPU.
$2.49/hr
spot avg
Don't have the hardware? Rent it.

Verified GPU rental prices across all major providers. Start in minutes, pay by the hour.

Compare GPU prices →LLM RAM calculatorSelf-host vs API calculator

Frequently Asked Questions

Should I self-host DeepSeek R1 or use the API?

For full R1, use the API — self-hosting requires an H100 cluster ($26,000+/month on RunPod) which only makes sense at enormous scale. For distilled variants, self-hosting on a single RTX 4090 or A100 is practical and cost-effective at moderate inference volumes.

How does R1 Distill quality compare to full R1?

R1 Distill Llama 70B retains about 90% of full R1's reasoning capability on MATH-500 and AIME. R1 Distill Qwen 32B retains about 80%. For most practical reasoning tasks, the 70B distill is the right choice — it's open, self-hostable, and nearly as capable.

Data verified 2026-08-20. GPU rental prices change frequently — verify before purchasing. See methodology.