gpt-oss 120B — MI300X vs MI355X
Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) and MI355X (AMD CDNA 4) on gpt-oss 120B. 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.
Setting 115 tok/s/user as the target on gpt-oss 120B, MI300X produces 1526 tok/s/GPU ($0.21 per million tokens) and MI355X produces 9458 ($0.04). MI355X is 376% cheaper per token; MI355X delivers 520% more tok/s/GPU.
At 160 tok/s/user interactivity on gpt-oss 120B, MI300X delivers 783 tok/s/GPU at $0.38 per million tokens; MI355X delivers 4781 tok/s/GPU at $0.09. MI355X is 346% cheaper per token; MI355X delivers 510% more tok/s/GPU at this point.
MI300X posts 303 tok/s/GPU for $0.99 per million tokens at 204 tok/s/user on gpt-oss 120B; MI355X posts 2688 tok/s/GPU for $0.15. MI355X is 552% cheaper per token; MI355X delivers 789% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | MI300X:1526.3MI355X:9458.1 | MI300X:783.4MI355X:4781.4 | MI300X:302.5MI355X:2688.0 |
| Cost ($/M tok) | MI300X:$0.205MI355X:$0.043 | MI300X:$0.383MI355X:$0.086 | MI300X:$0.992MI355X:$0.152 |
| tok/s/MW | MI300X:852664MI355X:3569076 | MI300X:437674MI355X:1804314 | MI300X:169003MI355X:1014337 |
| Concurrency | MI300X:~14MI355X:~42 | MI300X:~5MI355X:~15 | MI300X:~7MI355X:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.