KTS-1 standard

KTS-1 adaptive capacity

Measured · 32 people × 4K new (distinct inputs)

Measured on one configuration (variant ce7a1141), 3 repeats. Per-person values for each repeat are in this run’s OLIR JSON.

Repeats · 3

Recorded repeats for this run
Repeat	Each person · median	Machine total	First word · median	Slowest first word	Overlapping decodes	Power · median	Energy	Tokens per kWh	Service bar	Run
1	9.56 tok/s	157.40 tok/s	12.97 s	19.39 s	32	12.3 W	0.00047 kWh	6,177,336	missed	Run 93f3eb0f →
2	9.77 tok/s	157.59 tok/s	12.69 s	19.10 s	32	12.4 W	0.00048 kWh	6,104,893	missed	Run 93f3eb0f →
3	9.78 tok/s	157.71 tok/s	12.79 s	19.21 s	32	12.5 W	0.00049 kWh	5,990,685	missed	Run 93f3eb0f →

Method revision: KTS-1/adaptive-capacity-v2
Protocol SHA-256: 25fe3b0656961091ac1dfcc41df0b8cce189498814bf6c134c310f95ac15d1b0
Implementation SHA-256: 2de3c503cd76f5fc9ce6d5148760c219ddb52ee5cfbf5d728c3697037536d047
Cell outcome SHA-256: 7b93a8ec94506499f1376e6f8aed76a4176ad98d392bd9ea385a4acfbb2ffd13

Attempts · 2

Attempts recorded for this cell
Role	Classification	Capacity boundary	Configuration	Attempt SHA-256	Run
primary	capacity	serialization boundary	415588da	51ec5c7fa01a6e5f9b4dc61cdad0bf943e848fa45a62b4e7e75b2e5f22b1ced8	Run 93f3eb0f →
confirmation	measured	none	ce7a1141	650495fee713060896c55d5c526baa2784ac0ad0e2825075d74c850af8c5f2a1	Run 93f3eb0f →

Runs on this setup

Earlier runs keep their own engine versions and outcomes. Workload shapes stay separate.

History and measured sweep

History of this setup, newest first
Date	Cell or block	Each person · median	Result	Run
2026-10-18	64 people · 4K · new	4.30 tok/s	Measured	Run 4301ebe8 →
2026-10-18	32 people · 4K · new	9.77 tok/s	Measured	Run 93f3eb0f →

Answer checks

No answer-quality suite was graded for this run.

Method

KTS-1 adaptive-capacity-v2, owner amendment 2026-10-14. Ascending concurrency per context; one different same-model configuration confirmation of observed capacity. Limits have no numeric measurements.

Limits

Labelled lab evidence for the recorded setup and standard. Completion is coverage, not customer or general answer-quality qualification.

What ran

Exact identity

Original publisher model: Qwen3.6-35B-A3B
Publisher revision: not recorded
Variant · format · precision: NVFP4 variant · safetensors · nvfp4
Weights SHA-256: 07141c2db92e47bc08777132cd1a0323faf300eab3a7d7c111bc2bf075fda050
6dea9c759a0f941cf9e1cc1501216b0e107966a66c90425050e212efbd053f02
9758875fc55e49561165f4a44342b654c123c3e25c6811b34abb83553fb1a164
Engine · version · feature: NVIDIA NGC vLLM · 0.29.0+5013de39.dev · plain
Hardware: NVIDIA GB10, 128 GB unified memory
Harness / workload: not recorded
Workload suite · version: not recorded
Harness SHA-256: not recorded
Fixture SHA-256: not recorded

Workload shape

adaptive variant sha256: ce7a11417103cc42fa9c8145854c46461d126b984c768acf8e243600a467a158
cache state: cold
People in this run: 32
Configured window (tokens): 262144
Configured window (tokens): 4000
scenario: distinct

Full reproduction pack available to customers and evaluators on request

All recorded numbers

Metric definitions, scope and statistics

All aggregate numeric result fields in this run
Metric	Value	Scope	Statistic	Sample count	Basis / source field	Run
median decode tps	9.77 tok/s	per person	median	not recorded	standard_result.median_decode_tps	Run 93f3eb0f →
n	3.00 count	machine total	single	not recorded	standard_result.n	Run 93f3eb0f →

Data and citation

Download this run · OLIR JSON All numbers · CSV OLIR schema

Skilak Keep evidence, run 93f3eb0f88f141a897062601, measured 2026-10-18T20:06:17.782400+00:00.
https://skilak.ai/keep/resources/evidence/r/93f3eb0f88f141a897062601