LLM Inference Benchmark Explorer

Kimi-K2.5 on DGX B300 — NVFP4, vLLM, TP4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelKimi-K2.5
Parameters1.03T
Intelligence Index23.5
Agentic Index—
DeviceDGX B300
QuantizationNVFP4
Max C64+
Chat Capacity171
Agentic Capacity42
TP4
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
164128.78PASS
296113.38PASS
494104.33PASS
812087.38PASS
1619768.52PASS
3222556.73PASS
6426343.01PASS

In OpenZeka's measurement, Kimi-K2.5 (1.03T parameters), served in NVFP4 format with vLLM on DGX B300 (TP=4), reached a generation speed of 128.8 tok/s per request and a time to first token (TTFT) of 64 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 171 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.

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