KTS-1 adaptive capacity
Measured · 8 people × 4K new (distinct inputs)
Measured on one configuration (variant 415588da), 3 repeats. Per-person values for each repeat are in this run’s OLIR JSON.
Repeats · 3
| Repeat | Each person · median | Machine total | First word · median | Slowest first word | Overlapping decodes | Power · median | Energy | Tokens per kWh | Service bar | Run |
|---|---|---|---|---|---|---|---|---|---|---|
1 | 40.86 tok/s | 224.24 tok/s | 5.53 s | 6.09 s | 8 | 12.0 W | 0.00016 kWh | 4,466,062 | met | |
2 | 43.17 tok/s | 261.80 tok/s | 4.38 s | 4.78 s | 8 | 12.1 W | 0.00016 kWh | 4,607,904 | met | |
3 | 44.04 tok/s | 273.74 tok/s | 4.38 s | 4.78 s | 8 | 12.2 W | 0.00016 kWh | 4,513,117 | met |
- Method revision
KTS-1/adaptive-capacity-v2- Protocol SHA-256
25fe3b0656961091ac1dfcc41df0b8cce189498814bf6c134c310f95ac15d1b0- Implementation SHA-256
2de3c503cd76f5fc9ce6d5148760c219ddb52ee5cfbf5d728c3697037536d047- Cell outcome SHA-256
bb17a8770bc85adb3c44c168446e467e15bdb881e979f1dedbab3799bcc4efd4
Attempts · 1
| Role | Classification | Capacity boundary | Configuration | Attempt SHA-256 | Run |
|---|---|---|---|---|---|
primary | measured | none | 415588da | f38782e538d4ad135cd4cb3d687ebb142bc4867583d1d64e893e115dc9aad99c |
Runs on this setup
Earlier runs keep their own engine versions and outcomes. Workload shapes stay separate.
History and measured sweep
| Date | Cell or block | Each person · median | Result | Run |
|---|---|---|---|---|
2026-10-19 | 5 people · 250K · already read | 35.94 tok/s | Measured | |
2026-10-19 | 2 people · 250K · already read | 49.98 tok/s | Measured | |
2026-10-19 | 1 people · 250K · already read | 61.49 tok/s | Measured | |
2026-10-19 | 5 people · 250K · new | 18.82 tok/s | Measured | |
2026-10-19 | 2 people · 250K · new | 30.96 tok/s | Measured | |
2026-10-19 | 1 people · 250K · new | 61.96 tok/s | Measured | |
2026-10-18 | 5 people · 128K · new | 25.02 tok/s | Measured | |
2026-10-18 | 2 people · 128K · new | 45.22 tok/s | Measured | |
2026-10-18 | 1 people · 128K · new | 73.46 tok/s | Measured | |
2026-10-18 | 8 people · 64K · new | 6.88 tok/s | Measured | |
2026-10-18 | 5 people · 64K · new | 44.58 tok/s | Measured | |
2026-10-18 | 2 people · 64K · new | 59.94 tok/s | Measured | |
2026-10-18 | 1 people · 64K · new | 88.61 tok/s | Measured | |
2026-10-18 | 8 people · 40K · new | 7.62 tok/s | Measured | |
2026-10-18 | 5 people · 40K · new | 49.71 tok/s | Measured | |
2026-10-18 | 2 people · 40K · new | 73.60 tok/s | Measured | |
2026-10-18 | 1 people · 40K · new | 93.71 tok/s | Measured | |
2026-10-18 | 20 people · 4K · new | 16.74 tok/s | Measured | |
2026-10-18 | 16 people · 4K · new | 23.50 tok/s | Measured | |
2026-10-18 | 8 people · 4K · new | 43.17 tok/s | Measured | |
2026-10-18 | 5 people · 4K · new | 65.78 tok/s | Measured | |
2026-10-18 | 2 people · 4K · new | 86.44 tok/s | Measured | |
2026-10-18 | 1 people · 4K · new | 104.04 tok/s | Measured |
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
07141c2db92e47bc08777132cd1a0323faf300eab3a7d7c111bc2bf075fda0506dea9c759a0f941cf9e1cc1501216b0e107966a66c90425050e212efbd053f029758875fc55e49561165f4a44342b654c123c3e25c6811b34abb83553fb1a164- 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
- 415588daa437380e860555f3e55a80e6b6c9c4c8dce429d6c940f2fb436ef261
- cache state
- cold
- People in this run
- 8
- 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
| Metric | Value | Scope | Statistic | Sample count | Basis / source field | Run |
|---|---|---|---|---|---|---|
median decode tps | 43.17 tok/s | per person | median | not recorded | standard_result.median_decode_tps | |
n | 3.00 count | machine total | single | not recorded | standard_result.n |
Data and citation
Skilak Keep evidence, run 88c14bb0493e49208785570b, measured 2026-10-18T19:46:23.059075+00:00. https://skilak.ai/keep/resources/evidence/r/88c14bb0493e49208785570b
