LLM Inference Benchmark Explorer

GLM-5.3-Flash on 4× DGX Spark — FP8, vLLM, TP4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGLM-5.3-Flash
Parameters321B
Intelligence Index41.8
Agentic Index50.9
Device4× DGX Spark
QuantizationFP8
Max C2
Chat Capacity8
Agentic Capacity3
TP4
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
138329.61PASS
255820.85PASS
470613.52FAIL

In OpenZeka's measurement, GLM-5.3-Flash (321B parameters), served in FP8 format with vLLM on 4× DGX Spark (TP=4), reached a generation speed of 29.6 tok/s per request and a time to first token (TTFT) of 383 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 8 users for chat use and 3 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.

Notes: Model: zai-org/GLM-5.3-Flash, 500K context (full-precision FP8)

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