# Latency of one decision benchmark · Kai — Hanzo AI

> Time to one decision, by serving mode and device. No baseline was timed on the same hardware, so these stand alone.

[Benchmarks](https://hanzo.ai/benchmarks) / [Kai](https://hanzo.ai/benchmarks?product=Kai#all) / Latency of one decision

Kai · Latency

# Latency of one decision

Time to one decision, by serving mode and device. No baseline was timed on the same hardware, so these stand alone.

## Latest

[19.8 msp50 latency · Kai a7 · 0834a74f · cold, ROCM BF16no baseline · Unscored · Sep 28, 2026 · Hanzo-measured](#history)

[29.0 msp95 latency · Kai a7 · 0834a74f · cold, ROCM BF16no baseline · Unscored · Sep 28, 2026 · Hanzo-measured](#history)

## History

2 results across 2 metrics, newest first. Superseded runs stay, so a revision's progress can be read.

Measured

Subject

Metric

Value

Baseline

Result

Status

Sep 28, 2026

Kai a7 · 0834a74f · cold, ROCM BF16

p50 latency

19.8 ms

–

Unscored

Live · Hanzo-measured

Sep 28, 2026

Kai a7 · 0834a74f · cold, ROCM BF16

p95 latency

29.0 ms

–

Unscored

Live · Hanzo-measured

## Conditions

cold/rocm-bf16: encoder 768 wide, 22 layers

## Hardware

on evo

## Source

[research run latency-pool-a7.0834a74f-kai](https://api.hanzo.ai/v1/research/runs?org=hanzo&id=latency-pool-a7.0834a74f-kai)

## Reproduce

`bench speed --states results/states.json.gz --results capability/results --who kai --kai `

## More Kai benchmarks

[AG News](https://hanzo.ai/benchmarks/kai-ag-news) · [DAIR Emotion](https://hanzo.ai/benchmarks/kai-dair-emotion) · [Banking77](https://hanzo.ai/benchmarks/kai-banking77) · [Support triage](https://hanzo.ai/benchmarks/kai-support-triage) · [Email spam](https://hanzo.ai/benchmarks/kai-email-spam) · [Phishing](https://hanzo.ai/benchmarks/kai-phishing) · [Jailbreak](https://hanzo.ai/benchmarks/kai-jailbreak) · [Toxicity](https://hanzo.ai/benchmarks/kai-toxicity) · [RAG relevance](https://hanzo.ai/benchmarks/kai-rag-relevance) · [Model routing](https://hanzo.ai/benchmarks/kai-model-routing) · [Typed decisions](https://hanzo.ai/benchmarks/kai-typed-decisions) · [MASSIVE](https://hanzo.ai/benchmarks/kai-massive) · [AG News, validation split](https://hanzo.ai/benchmarks/kai-ag-news-validation-split) · [Support triage, validation split](https://hanzo.ai/benchmarks/kai-support-triage-validation-split) · [Typed decisions, validation split](https://hanzo.ai/benchmarks/kai-typed-decisions-validation-split) · [HarmBench (benign prompts)](https://hanzo.ai/benchmarks/kai-harmbench) · [Choosing among many options](https://hanzo.ai/benchmarks/kai-choice-size) · [Joint decisions](https://hanzo.ai/benchmarks/kai-joint) · [Release gate against Jev](https://hanzo.ai/benchmarks/kai-release-gate)

[Every result for Latency of one decision on the shelf](https://hanzo.ai/benchmarks?q=Latency%20of%20one%20decision#all) · [How these are measured](https://hanzo.ai/benchmarks#methods)