LLM Inference Benchmark Explorer

Qwen3.5-27B on RTX PRO 6000 — FP8, vLLM, TP1 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3.5-27B
Parameters27B
Intelligence Index22.9
Agentic Index—
DeviceRTX PRO 6000
QuantizationFP8
Max C32
Chat Capacity60
Agentic Capacity20
TP—
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
16628.61PASS
212226.38PASS
412125.73PASS
813726.15PASS
1621925.14PASS
3237924.18PASS
6477219.15FAIL

In OpenZeka's measurement, Qwen3.5-27B (27B parameters), served in FP8 format with vLLM on RTX PRO 6000, reached a generation speed of 28.6 tok/s per request and a time to first token (TTFT) of 66 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 60 users for chat use and 20 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.