STRATA Reserve capacity
Strata/Answers/Sizing

How many GPUs do I need to run DeepSeek V3 or R1 (671B)?

SizingUpdated 2026-10-23

DeepSeek V3 and R1 have 671B parameters, about 700 GB in their native FP8, so the usual setup is one 8×H200 node (1,128 GB) or one 8×B200 node; 8×H100 (640 GB) only works with 4-bit quantization or two nodes. At Strata GPU an 8×H200 node costs about $25,170 per month on demand or $21,647 reserved for 24–36 months.

Reserve capacityAll GPUs and prices

Options

SetupGPU memoryFits
8× H2001,128 GBFP8 with room for KV cache
8× B200≈ 1,440 GB usableFP8 with large batches, FP4 option
8× H100640 GB4-bit only, or 16× H100 across two nodes for FP8

Distilled models

If you need R1-style reasoning without the full model, the distilled 32B and 70B versions run on one or two GPUs. See GPU for a 70B model.

FAQ
Is a mixture-of-experts model cheaper to serve?

Per token, yes: only about 37B parameters are active per token. But all 671B must still be in GPU memory.

Can I reserve an 8×H200 node for three months?

Yes. Reserved clusters start at one 8-GPU node for three months.

NVIDIA H200 141GB
Hopper · 141 GB HBM3e

H200

from $4.31/GPU-hr

Specs and pricing →
NVIDIA B200 192GB
Blackwell · 192 GB HBM3e

B200

Pricing on request

Specs and pricing →
Related questions

How much does it cost to rent an H100 per hour in 2026? How much does it cost to rent an H200 GPU? How much does it cost to rent an NVIDIA B200? What are the best RunPod alternatives for renting GPUs?