GLM 5.3 744B — MI355X vs TPU7x
Head-to-head AI inference benchmark comparison of MI355X (AMD CDNA 4) and TPU7x (Google Ironwood) on GLM 5.3 744B. 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
MI355X hits 17312 tok/s/chip for $0.02 per million tokens at 71 tok/s/user on GLM 5.3 744B. No TPU7x data at this operating point.
MI355X: 9604 tok/s/chip, $0.04 per million tokens at 140 tok/s/user on GLM 5.3 744B. TPU7x is unmeasured here.
At 208 tok/s/user on GLM 5.3 744B, MI355X delivers 4830 tok/s/chip at $0.09 per million tokens; TPU7x hasn't been benchmarked at this target. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI355X:17311.5TPU7x:— | MI355X:9603.7TPU7x:— | MI355X:4829.5TPU7x:— |
| Cost ($/M tok) | MI355X:$0.024TPU7x:— | MI355X:$0.043TPU7x:— | MI355X:$0.086TPU7x:— |
| tok/s/MW | MI355X:8283022TPU7x:— | MI355X:4595060TPU7x:— | MI355X:2310788TPU7x:— |
| Concurrency | MI355X:~14TPU7x:— | MI355X:~5TPU7x:— | MI355X:~2TPU7x:— |