LLM Inference Benchmark Explorer

GLM-5.3-Flash on DGX B300 — FP8, SGLang, TP2 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGLM-5.3-Flash
Parameters321B
Intelligence Index41.8
Agentic Index50.9
DeviceDGX B300
QuantizationFP8
Max C8
Chat Capacity32
Agentic Capacity12
TP2
DP—
PP—
EngineSGLang
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
1262211.42PASS
2687102.56PASS
435390.33PASS
841059.70PASS
16195439.75FAIL
32425120.93FAIL
64451122.43FAIL

In this measurement, GLM-5.3-Flash (321B parameters), served in FP8 format with SGLang on DGX B300 (TP=2), reached a generation speed of 211.4 tok/s per request and a time to first token (TTFT) of 262 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 32 users for chat use and 12 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.