LLM Inference Benchmark Explorer

Kimi-K2.6 on DGX B300 — INT4, vLLM, TP4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelKimi-K2.6
Parameters1.03T
Intelligence Index27
Agentic Index20.5
DeviceDGX B300
QuantizationINT4
Max C32+
Chat Capacity128+
Agentic Capacity42
TP4
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
156220.75PASS
2115159.74PASS
486130.38PASS
8107102.35PASS
1615175.93PASS
3235658.55PASS

In this measurement, Kimi-K2.6 (1.03T parameters), served in INT4 format with vLLM on DGX B300 (TP=4), reached a generation speed of 220.8 tok/s per request and a time to first token (TTFT) of 56 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is at least 128 users for chat use and 42 for agentic use. The realistic capacity will likely fall between these two values. In scenarios dominated by coding, tool use, long workflows and multi-agent use, capacity approaches the agentic estimate; where shorter interactions, standard conversations and lighter tasks dominate, it approaches the chat estimate.

“At least” means the configuration met the speed targets even at the highest load tested, so the real capacity may be higher.

Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.