Research report in English · KyaniteLabs Research. First published September 28, 2026. Original public report. This edition consolidates the report and preserves its original limits.
The nmax2 drafter accepted 72.2% against 22.7% for the draft-12 control in this measured workload. Acceptance is one result. The throughput figures and the limits belong beside it.
The reported measurements
- Draft-12 control: 17.5 tokens per second.
- nmax2-np2: 25.4 tokens per second.
- nmax3: 28.5 tokens per second.
- nmax4: 23.9 tokens per second.
- Engine comparison on the same box: HIP 20.8 tokens per second; Vulkan 9.2.
The nmax3 figure is higher than nmax2-np2 in the reported run. That does not turn this short report into a universal configuration ranking. The original report does not supply sample counts, confidence intervals, every comparison table or a full reproduction recipe.
What backs these numbers
The September 28 report states that every figure was dual-verified. Its named verification record is research/floor-optimization/window4/W4-VERIFICATION-RECEIPT-20260925.md. That is the original report's provenance statement; this page does not claim a new independent verification of the underlying experiment.
Limits
One lab, one box class and the lab's own workloads. No external reproduction is claimed. Acceptance percentages are not tokens per second, and these figures do not establish a general speedup for other hardware or models.
This edition preserves the already-public measurements. It adds no new experimental result.