LLM Inference Benchmark Explorer

GLM-5.3-Flash on 2× DGX Spark — NVFP4, vLLM, TP2 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGLM-5.3-Flash
Parameters321B
Intelligence Index41.8
Agentic Index50.9
Device2× DGX Spark
QuantizationNVFP4
Max C1
Chat Capacity2
Agentic Capacity1
TP2
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
139524.34PASS
257517.66FAIL
476513.58FAIL
843008.94FAIL
16189004.51FAIL

In OpenZeka's measurement, GLM-5.3-Flash (321B parameters), served in NVFP4 format with vLLM on 2× DGX Spark (TP=2), reached a generation speed of 24.3 tok/s per request and a time to first token (TTFT) of 395 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 2 users for chat use and 1 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: LibertAIDAI/GLM-5.3-Flash-NVFP4. Docker: radixark/vllm-glm53-flash:sm121-v8

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