With a fixed 512-token sparse budget on Qwen3-8B/LB[16k-18k], sweeping page size from 1 to 64 produced 1,334–1,451 output tok/s and 81.2–88.3% acceptance. The paper reports throughput varied by under 9% over the 64× granularity range and page size 16 was near the peak, not at the maximum.

With a fixed 512-token sparse budget on Qwen3-8B/LB[16k-18k], sweeping page size from 1 to 64 produced 1,334–1,451 output tok/s and 81.2–88.3% acceptance. The paper reports throughput varied by under 9% over the 64× granularity range and page size 16 was near the peak, not at the maximum. · CiteArk

Measurement results

0/12 assessed

0 supported0 disputed or conflicting12 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
pageSizeTokens: 1	1,430 output token/s	—	Not assessed
pageSizeTokens: 1	86.8%	—	Not assessed
pageSizeTokens: 4	1,389 output token/s	—	Not assessed
pageSizeTokens: 4	84.7%	—	Not assessed
pageSizeTokens: 8	1,451 output token/s	—	Not assessed
pageSizeTokens: 8	88.3%	—	Not assessed
pageSizeTokens: 16	1,437 output token/s	—	Not assessed
pageSizeTokens: 16	86.8%	—	Not assessed
pageSizeTokens: 32	1,334 output token/s	—	Not assessed
pageSizeTokens: 32	81.2%	—	Not assessed
pageSizeTokens: 64	1,394 output token/s	—	Not assessed
pageSizeTokens: 64	84.1%	—	Not assessed

With a fixed 512-token sparse budget on Qwen3-8B/LB[16k-18k], sweeping page size from 1 to 64 produced 1,334–1,451 output tok/s and 81.2–88.3% acceptance. The paper reports throughput varied by under 9% over the 64× granularity range and page size 16 was near the peak, not at the maximum.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results