​
Benchmarks & methodology

Evidence behind hardware and mining claims in the Litepaper. Last reviewed: July 2026.
Malibu publishes two different performance stories. They must not be conflated: A strong PoMW walk result does not automatically imply the same per-watt advantage on inference TPS. This page scopes the published PoMW numbers.

​
PoMW Phase 1 benchmark (M5 Air)

Source: internal Phase 1 Metal port report (mining-prototype-phase1.md spec; results captured July 2026 on an M5 Air).

​
What this proves

  • The PoMW algorithm runs correctly and efficiently on Apple Silicon Metal.
  • The walk is memory-substrate bound — the workload Malibu targets for mining readiness.
  • Byte-exact determinism against a reference implementation is reproducible.

​
What this does not prove

  • Inference tokens/sec on buyer workloads.
  • That every Mac tier sustains the same thermal profile (fanless Air throttles under long runs).
  • Cross-hardware superiority on workloads other than this specific walk.

​
10× per-watt vs RTX 5090 (scoped claim)

The Litepaper cites roughly 10× better per-watt efficiency vs an RTX 5090 on PoMW memory-hard weight walks only — not on inference TPS. Methodology note: GPU numbers use the same walk algorithm ported to the comparison substrate where available. This is a mining-substrate comparison, not a buyer inference benchmark. Do not extrapolate to chat-completion pricing or latency.

​
Inference benchmarks (not yet published)

Malibu does not yet publish a cross-tier inference TPS table on /docs. Buyer value claims (latency, throughput, cost) should be validated against:
  • Live GET /v1/rate-card for current pricing
  • Your workload on api.malibu.tech/v1 with pinned providers when reproducibility matters
When inference benchmarks ship, they will appear on this page with hardware tier, model, context length, and date.

​
Market sizing claims

Treat fleet-utilization numbers as planning inputs, not audited network telemetry.

​
Reproduce PoMW results

The Phase 1 spec lives in mining-prototype-phase1.md. When the public miner probe repository ships, rerun the benchmark harness on your Mac class and compare against the M5 Air baseline above.