- First word afterttft_median_s · s
- 373.11 sper person · median of 5
- Slowest first wordttft_max_s · s
- 611.98 sper person · max of 5
- Machine totalaggregate_decode_tps · tok/s
- 1.07 tok/smachine total · single · sample count not recorded
- Machine total including first-word waitaggregate_e2e_tps · tok/s
- 0.86 tok/smachine total · single · sample count not recorded
- Everyone answered inwall_seconds · s
- 618.65 smachine total · single · sample count not recorded
- Peak memory, whole hostpeak_host_unavailable_gib · GiB
- 36.21 GiBmachine total · max · sample count not recorded
Runs on this setup
Earlier runs keep their own engine versions and outcomes. Workload shapes stay separate.
History and measured sweep
| Date | Shape | Each person · median | Machine total | First word · median | Result | Run |
|---|---|---|---|---|---|---|
2026-10-07 | 5 people · shared · warm | not recorded | 1.09 tok/s | 356.62 s | Failed | |
2026-10-07 | 5 people · shared · cold | not recorded | 1.07 tok/s | 373.11 s | Failed | |
2026-10-07 | 5 people · distinct · cold | not recorded | 0.88 tok/s | 375.66 s | Failed | |
2026-10-07 | 1 people · distinct · cold | not recorded | 31.17 tok/s | 118.04 s | Passed | |
2026-10-06 | 5 people · distinct · cold | not recorded | 0.95 tok/s | 357.17 s | Failed | |
2026-10-06 | 1 people · distinct · cold | not recorded | 30.59 tok/s | 115.22 s | Failed |
Each person in this run
First-word wait against writing speed after that word, including pauses. Earlier streams can pause while other people’s prompts are read. The table preserves filled input, cached-token counts and each person’s checks.
Per-person table · all measured request rows
| Person | Filled input | Cached tokens | Output | First word | Writing after first word | Total time | Checks | Run |
|---|---|---|---|---|---|---|---|---|
2 | 250,016 | 0 | 96 | 124.22 s | 0.25 tok/sone person · includes waits | 502.70 s | 3/3 Hidden facts found · completed · checks passed | |
3 | 250,016 | 0 | 107 | 250.40 s | 0.29 tok/sone person · includes waits | 613.47 s | 3/3 Hidden facts found · completed · checks passed | |
4 | 250,016 | 0 | 110 | 373.11 s | 0.45 tok/sone person · includes waits | 615.98 s | 3/3 Hidden facts found · completed · checks passed | |
5 | 250,016 | 0 | 109 | 494.35 s | 0.88 tok/sone person · includes waits | 617.64 s | 3/3 Hidden facts found · completed · checks passed | |
1 | 250,016 | 0 | 110 | 611.98 s | 16.38 tok/sone person · includes waits | 618.64 s | 3/3 Hidden facts found · completed · checks passed |
Per-person table · all measured request rows
| Person | Filled input | Cached tokens | Output | First word | Writing after first word | Total time | Checks | Run |
|---|---|---|---|---|---|---|---|---|
2 | 250,016 | 0 | 96 | 124.22 s | 0.25 tok/sone person · includes waits | 502.70 s | 3/3 Hidden facts found · completed · checks passed | |
3 | 250,016 | 0 | 107 | 250.40 s | 0.29 tok/sone person · includes waits | 613.47 s | 3/3 Hidden facts found · completed · checks passed | |
4 | 250,016 | 0 | 110 | 373.11 s | 0.45 tok/sone person · includes waits | 615.98 s | 3/3 Hidden facts found · completed · checks passed | |
5 | 250,016 | 0 | 109 | 494.35 s | 0.88 tok/sone person · includes waits | 617.64 s | 3/3 Hidden facts found · completed · checks passed | |
1 | 250,016 | 0 | 110 | 611.98 s | 16.38 tok/sone person · includes waits | 618.64 s | 3/3 Hidden facts found · completed · checks passed |
Answer checks
15/15 Hidden facts found5/5 request checks
Method
Synchronized long public-domain prompts, three exact hidden facts per user. Decode rate uses completion tokens minus one over first output through stream completion; effective prefill includes scheduling and first-token latency. Aggregate decode uses the union window from first output to final completion; end-to-end rate includes prefill.
Limits
Lab observation, not customer acceptance. Prompt content length excludes the server chat template; actual per-request usage is recorded. Synthesis is requested and retained but semantic accuracy is unassessed. All requested users must overlap in observed decode to pass.
What did not work
- Observed decode overlap was 4 of 5 requested users.
What ran
Exact identity
- Original publisher model
- NVIDIA-Nemotron-3.5-Lightning-30B-A3B
- Publisher revision
a9904d24bcc1d289a1950fa9d2b978c47cf903b9- Variant · format · precision
- Q4_K_M GGUF variant · GGUF · Q4_K_M
- Weights SHA-256
- not recorded
- Engine · version · feature
- llama.cpp CUDA ·
version not recorded· plain - Hardware
- NVIDIA GB10, 128 GB unified memory
- Harness / workload
keep-long-context-concurrency-v1 · 1- Workload suite · version
not recorded- Harness SHA-256
not recorded- Fixture SHA-256
04e5839fffd3856049c11c680e5ae05a807f32bbf3dec72f7a00578188171f70
Workload shape
- cache state
- cold
- People in this run
- 5
- Configured window (tokens)
- 262144
- Filled content target (tokens)
- 250000
- fixture variant
- shared-record-groups-v2
- KV cache precision
- q8_0
- Output token ceiling
- 512
- scenario
- shared
- Thinking
- off
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 |
|---|---|---|---|---|---|---|
wall seconds | 618.65 s | machine total | single | not recorded | wall_seconds | |
ttft median s | 373.11 s | per person | median | 5 | ttft_median_s | |
hidden facts total | 15.00 count | machine total | single | not recorded | needle_total | |
ttft max s | 611.98 s | per person | max | 5 | ttft_max_s | |
requests ok | 5.00 count | machine total | single | not recorded | requests_ok | |
hidden facts correct | 15.00 count | machine total | single | not recorded | needle_correct | |
latency bar seconds | 300.00 s | machine total | single | not recorded | latency_bar_seconds | |
decode overlap | 4.00 count | machine total | single | not recorded | decode_overlap | |
aggregate concurrency | 5.00 count | machine total | single | not recorded | aggregate_concurrency | |
requests total | 5.00 count | machine total | single | not recorded | requests_total | |
aggregate decode tps | 1.07 tok/s | machine total | single | not recorded | aggregate_tps | |
aggregate e2e tps | 0.86 tok/s | machine total | single | not recorded | aggregate_end_to_end_tps | |
peak host unavailable gib | 36.21 GiB | machine total | max | not recorded | peak_host_unavailable_gib |
Data and citation
Skilak Keep evidence, run 2e4b0560b64e49cdbf82d029, measured 2026-10-07T01:16:53.994768+00:00. https://skilak.ai/keep/resources/evidence/r/2e4b0560b64e49cdbf82d029
