LLM Inference Benchmark Explorer

GLM-5.2 on 4× DGX Spark — INT4, vLLM, TP4, speculative decoding k=4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGLM-5.2
Parameters753B
Intelligence Index33.7
Agentic Index38.4
Device4× DGX Spark
QuantizationINT4
Max C2
Chat Capacity8
Agentic Capacity3
TP4
DP—
PP—
EnginevLLM
Speculative DecodingYes
CTTFT (ms)TPS (tok/s)Status
149027.39PASS
271720.02PASS
495514.33FAIL
865608.51FAIL

In OpenZeka's measurement, GLM-5.2 (753B parameters), served in INT4 format with vLLM and speculative decoding on 4× DGX Spark (TP=4), reached a generation speed of 27.4 tok/s per request and a time to first token (TTFT) of 490 ms with a single request.

Considering the speed targets alone (the KV cache limit was not calculated for this configuration), 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: TP=4, DCP=4, cudagraph FULL, GMU 0.885, B12X_MLA_SPARSE

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