- Machine totalaggregate_e2e_tps · tok/s
- 59.16 tok/smachine total · single · 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 |
|---|---|---|---|---|---|---|
2026-10-05 | 2 people | not recorded | 59.16 tok/s | not recorded | Partial | |
2026-10-05 | unknown people | not recorded | not recorded | not recorded | Partial | |
2026-10-05 | unknown people | not recorded | not recorded | not recorded | Partial |
Answer checks
16/16 tasks
Method
Sixteen exact-output tasks and repeated greedy controls per candidate; warm four-request code/chat throughput includes first-token time and final drain.
Limits
The selected candidate passed its bounded checks; rejected and unfinished candidates remain in the table. Configured context is not long-context quality proof.
What did not work
- The selected candidate passed its bounded checks; rejected and unfinished candidates remain in the table.
What ran
Exact identity
- Original publisher model
- Qwen3.8-27B
- Publisher revision
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0- Variant · format · precision
- NVFP4 variant · safetensors · NVFP4
- Weights SHA-256
- not recorded
- Engine · version · feature
- SGLang ·
version not recorded· speculative decoding - 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
- People in this run
- 2
- Configured window (tokens)
- 262144
- KV cache precision
- fp8_e4m3
- Feature
- speculative decoding
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 |
|---|---|---|---|---|---|---|
workload total | 16.00 count | machine total | single | not recorded | workload_total | |
workload passed | 16.00 count | machine total | single | not recorded | workload_passed | |
tuning candidates | 9.00 count | machine total | single | not recorded | tuning_candidates | |
aggregate concurrency | 2.00 count | machine total | single | not recorded | aggregate_concurrency | |
rejected candidates | 4.00 count | machine total | single | not recorded | rejected_candidates | |
aggregate e2e tps | 59.16 tok/s | machine total | single | not recorded | aggregate_tps |
Data and citation
Skilak Keep evidence, run d732a4ff7cc1dd9ae54bd9e0, measured 2026-10-05T16:30:42.252659+00:00. https://skilak.ai/keep/resources/evidence/r/d732a4ff7cc1dd9ae54bd9e0
