MI355X: FP4 vs FP8 Precision Comparison
How FP4 and FP8 precision affect GLM 5.3 744B inference on MI355X (AMD CDNA 4). Throughput, latency, and cost across LLM workloads. Use the chart controls below to switch sequences and metrics — same interactions as the main inference chart.
At 522 tok/s/user on GLM 5.3 744B (MI355X), FP8 delivers 198 tok/s/chip at $2.11 per million tokens; FP4 hasn't been benchmarked at this target. (Numbers reflect the default 8k/1k selection for this URL — table and chart below update if you change sequence or model in the controls. Each side uses the best available serving configuration for that precision, which may include speculative decoding such as MTP where recipes exist — the same convention as the other comparison pages.)
| Metric | Interactivity (tok/s/user) |
|---|---|
| Throughput (tok/s/chip) | FP4:—FP8:197.8 |
| Cost ($/M tok) | FP4:—FP8:$2.106 |
| tok/s/MW | FP4:—FP8:94648 |
| Concurrency | FP4:—FP8:~1 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.