GLM 5.2 · GPU comparison

GLM 5.2 — H200 vs MI325X

Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and MI325X (AMD CDNA 3) on GLM 5.2. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.

View performance-per-dollar view →

No interpolated comparison data available for the default model. Use the chart controls below to select a model with benchmark data for both GPUs.

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.

Vendor:
Aggregation:
Spec Decoding: