Kimi K2.5/K2.6/K2.7-Code 1TNVIDIA Hopper
Running Kimi K2.6 on H200
Quick answer
Kimi K2.6 runs on H200: 15 benchmarked configs so far. See the interactivity ladder below for measured operating points.
Benchmarked configs
15
Serving engines
vLLM
Precisions
int4
Run dates
2026-03-27 → 2026-05-30
Throughput at every interactivity target
Serving is a trade-off: push more concurrent users through a GPU and each user's tokens arrive slower. The ladder below reads the measured frontier at each per-user speed target on a single-turn chat workload (8k input / 1k output), using the best engine and precision at that point.
| Per-user target | Tokens/s per GPU | $ / 1M tokens | Engine | Precision |
|---|---|---|---|---|
| 30 tok/s | - | - | - | - |
| 50 tok/s | - | - | - | - |
| 75 tok/s | - | - | - | - |
| 100 tok/s | - | - | - | - |
| 150 tok/s | - | - | - | - |
| 200 tok/s | - | - | - | - |
Frequently asked questions
- How fast is Kimi K2.6 on H200?
- The InferenceX fleet has 15 benchmarked configs for this pairing; see the interactivity ladder above for the operating points reached so far.
- How much does it cost to serve Kimi K2.6 on H200?
- Cost per million tokens is derived from measured throughput and $/GPU/hr rates from the SemiAnalysis AI Cloud TCO model; it appears once this pairing reaches the primary interactivity tier.
- Which serving engines run Kimi K2.6 on H200?
- The runs behind this page used vLLM in INT4. Engines are rebuilt and re-benchmarked continuously, so the best config can change between visits.
- How are these Kimi K2.6 numbers measured?
- Every number is measured on real H200 hardware by the InferenceX fleet, sweeping concurrency on a single-turn chat workload (8k input / 1k output) to trace the throughput-versus-interactivity frontier; the newest run landed on 2026-05-30. The same derivation powers the InferenceX overview leaderboard.