Skip to content
Bitpute
ToolsModelsGPUsCloudLearn

Multi-GPU planner

Plan the rig
before you build it.

2 × 4090 or 4 × H100 — see what a multi-card rig actually delivers: pooled VRAM, real decode speed after tensor-parallel overhead, wall power, and the full hardware cost with a buy-vs-rent call.

Pooled VRAM

Weights shard across cards — near-linear, minus overhead.

Honest speed

Decode scales sub-linearly; we apply TP efficiency.

Full cost

N× hardware + power, vs the same rig on cloud.

Rig configurationlive

Total VRAM
usable pooled
Speed
decode, this model
Power
at the wall
Hardware cost
N × price
Model fit
footprint vs pooled
Electricity / mo
whole rig
Cloud equiv / mo
same rig, rented
Buy-vs-rent
break-even
Pooled VRAM across the rig footprint / GB usable

How we model a rig

No linear-scaling myths.

VRAM

Weights and KV shard across cards, so capacity is N × per-card minus per-card runtime overhead. Near-linear, not perfect.

Speed

N × bandwidth ÷ weights × TP-eff. Tensor-parallel decode loses to all-reduce comms — ~0.9× at 2 cards, ~0.8× at 4, ~0.68× at 8.

Power & cost

Wall draw N × TDP × 1.3; hardware N × price; cloud N × $/hr. Break-even from the same cited cost model.

Cost a single card →

One big card or many small ones?

Size the whole cluster.

A rig only makes sense if the model needs it. The Workspace ranks single cards first — come here when one won't hold the job.

Evidence & method

How this calculation works

Estimates a model's total footprint, then computes how many GPUs of a given card are needed when it will not fit on one, using usable VRAM per card.

Data sources

  • NVIDIA, AMD & Intel GPU documentation
  • Hugging Face model cards
  • Official model papers
  • Bitpute Methodology

Assumptions

  • Weights = parameters × bits-per-weight ÷ 8
  • Runtime overhead = 0.75 GB + 5% of weights (CUDA context, allocator, buffers)
  • Recommended VRAM = total × 1.10 (10% headroom)
  • Usable VRAM = card capacity × 0.95
  • KV cache counted only when the model architecture is known; when applied, batch size 1, FP16 KV, context as entered
  • Splits the model across identical GPUs, sized by usable VRAM per card

Limitations

  • Actual VRAM varies by framework (PyTorch, llama.cpp, vLLM, TGI), driver/CUDA version and OS
  • Quantization implementations differ; real bits-per-weight can vary from the nominal value
  • When architecture is unknown the KV cache is omitted, so long-context use will exceed the estimate
  • Estimates are for planning and comparison, not a guarantee

Data status: Hardware specs — vendor documentation. Model metadata — community model cards, not independently verified.

Why does this estimate differ from other calculators?
  • Different footprint formulas and rounding
  • Different KV-cache assumptions (batch, context, precision)
  • Framework and inference-engine differences
  • Reserved and fragmented VRAM
  • Driver and CUDA overhead
  • Precision and quantization choices