LLM Inference Benchmark Explorer

GLM-4.5-Air on DGX B300 — BF16, vLLM, TP1 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGLM-4.5-Air
Parameters110B
Intelligence Index11.1
Agentic Index—
DeviceDGX B300
QuantizationBF16
Max C32+
Chat Capacity16
Agentic Capacity4
TP—
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
162112.74PASS
24077.94PASS
44466.45PASS
85851.55PASS
1611639.90PASS
3237230.68PASS

In this measurement, GLM-4.5-Air (110B parameters), served in BF16 format with vLLM on DGX B300, reached a generation speed of 112.7 tok/s per request and a time to first token (TTFT) of 62 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 16 users for chat use and 4 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.