Back to search

Multi-GPU Cluster Planner

Training a 70B parameter model does not fit on one GPU. Plan your cluster by selecting any LLM workload, adding GPU nodes, and mixing different cards. We calculate total VRAM, FP16 compute, power draw, and real cost estimates.

Supports Kimi K2.6, MiMo-V2.5-Pro, DeepSeek V4 Pro, Mercury 2, Granite 4.0, Command A+, Qwen3.5, Gemma 3n, and custom VRAM targets. Precision options include FP16, INT8, and FP4/GGUF. Cost estimates use live minimum prices from 12 cloud providers.

Model Requirements

Total VRAM Required
480 GB

Cluster Summary

Total GPUs
2
Total VRAM
160 GB
Total FP16
624 TFLOPS
Total Power
800 W
VRAM Utilization33%
Need 320 GB more VRAM

GPU Nodes

Node VRAM: 160 GB
Node FP16: 624 TFLOPS