Dontopedia
Explore

Measurement H40

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

Measurement H40 has 5 facts recorded in Dontopedia across 1 reference.

5 facts·5 predicates·1 sources

Mostly:has throughput tokens per second(1), measured on hardware(1), has sequence length(1)

Maturity scale raw canonical shape-checked rule-derived certified

Has Throughput Tokens Per SecondhasThroughputTokensPerSecond

  • 21642[1]sourceall time · 677

Measured on HardwaremeasuredOnHardware

Has Sequence LengthhasSequenceLength

  • 256[1]sourceall time · 677

Has Batch SizehasBatchSize

  • 16[1]sourceall time · 677

Measured ConfigurationmeasuredConfiguration

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

hasBatchSizeblah/watt-activation/677
16
hasSequenceLengthblah/watt-activation/677
256
hasThroughputTokensPerSecondblah/watt-activation/677
21642
measuredConfigurationblah/watt-activation/677
ex:model-config-h40
measuredOnHardwareblah/watt-activation/677
ex:m3-ultra

References (1)

1 references
  1. customctx:discord/blah/watt-activation/677
    • full textwatt-activation-677
      text/plain2 KBdoc:agent/watt-activation-677/0a3c1f90-3dc6-48cb-b08e-24d6d4275ede
      Show excerpt
      [2026-04-22 13:11] xenonfun: • For the H=40 preset (D=560, ~19.0M params), current measured GPU training is: ``` 21,642 tok/s at B=16, T=256 on M3 Ultra. I also tried nearby H values in multiples of 4: | H | D | Params | GPU tok/s |

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.