MeshAI
Simulation Lab

Simulate Before You Scale.

Explore workload behaviour across GPU configurations, architectures and operating conditions before committing capital. This functional preview uses a transparent client-side demonstration model, not the production MeshAI simulation engine.

SimulatedIllustrativeLocal engine v0.1 · not a production benchmark
Baseline versus MeshAI-optimised simulation results
Metric (illustrative)A · BaselineB · MeshAI-optimised
Quantisation / locationFP16 · on-premisesINT8 · on-premises
Model memory1638 GB (89% / accel)819 GB (85% / accel)
Accelerators required / available172 / 1625 / 16
Capacity utilisation100%100%
Accelerator utilisation100%100%
Throughput served / demand373 / 3,000 tok/s2,654 / 3,000 tok/s
Time to first token33,626 ms2,364 ms
End-to-end latency117,686 ms8,267 ms
Energy / day376.3 kWh (grid 346.2 · solar 0 · gen 0)376.3 kWh (grid 346.2 · solar 0 · gen 0)
Operating cost / month$18,942$18,942
Success rate12.43%88.46%
Cost per successful task$0.00490$0.00069
Resilience score34 / 10092 / 100
Sovereignty policyCompliantCompliant
Loading visualisations…
Baseline · recommendations
  • — Add 156 × NVIDIA H100 80GB to meet demand at 75% target utilisation.
  • — Latency target missed — reduce output length, quantise, or place closer to users.
Configuration as enteredStatic batching assumptionNo power or connectivity awareness
MeshAI-optimised · recommendations
  • — Add 9 × NVIDIA H100 80GB to meet demand at 75% target utilisation.
  • — Latency target missed — reduce output length, quantise, or place closer to users.
Recommends INT8 — quality preservation must be validated per model and languageContinuous batching assumptionPower-aware scheduling of deferrable workLocal fallback during connectivity outages
Assumptions, formulas & provenance

Note · Results come from a deterministic first-order model running in your browser. They are simulated, not measured, and carry wide uncertainty (memory-bound decode approximation, fixed batching efficiencies, simplified power and outage behaviour). Quantisation recommendations must be validated for quality per model and language.

Model memory
params × bytes/param × 1.2 overhead + KV cache (users × tokens × 0.0001 GB × params × bytes/2)
Per-sequence decode rate
accelerator bandwidth ÷ weight bytes (memory-bound decode)
Node throughput
decode rate × min(users, batch cap) × batching efficiency
Required accelerators
max(memory shards, demand tok/s ÷ (per-accel throughput × 75% target))
Latency
network RTT + input tokens ÷ (decode × 8) + output tokens ÷ decode rate
Energy
accelerators × watts × (30% idle + 70% × utilisation) × PUE × 24h
Cost / successful task
(compute + energy cost) ÷ (requests × success rate)
Success rate
availability after grid, battery and connectivity outages
Constant assumptions
{
  "bytesPerParam": {
    "fp16": 2,
    "int8": 1,
    "int4": 0.5
  },
  "weightOverhead": 1.2,
  "kvGBPerTokenPerBParamFp16": 0.0001,
  "prefillSpeedup": 8,
  "targetUtilisation": 0.75,
  "idlePowerFraction": 0.3,
  "pue": 1.4,
  "dieselUSDPerKWh": 0.45,
  "outageHours": 4,
  "offshoreLatencyMs": 140,
  "inCountryLatencyMs": 25,
  "baselineBatching": 0.35,
  "meshBatching": 0.65,
  "solarSunHours": 5.5
}
Next step

Need calibrated assumptions, measured infrastructure data or a broader capacity assessment?

Request a Detailed Infrastructure Assessment