LLM Inference Benchmark Explorer

GLM-4.6 on DGX B300 — BF16, vLLM, TP4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGLM-4.6
Parameters357B
Intelligence Index18.5
Agentic Index—
DeviceDGX B300
QuantizationBF16
Max C32+
Chat Capacity87
Agentic Capacity21
TP4
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
127562.10PASS
227056.02PASS
429951.48PASS
836047.05PASS
1637142.24PASS
3237234.20PASS

In OpenZeka's measurement, GLM-4.6 (357B parameters), served in BF16 format with vLLM on DGX B300 (TP=4), reached a generation speed of 62.1 tok/s per request and a time to first token (TTFT) of 275 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 87 users for chat use and 21 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.