MiniMax M2.5/M2.7 — MI300X vs MI355X
Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) and MI355X (AMD CDNA 4) on MiniMax M2.5/M2.7. 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.
MI300X / MI355X on MiniMax M2.5/M2.7 at 44 tok/s/user: 1249 / 3638 tok/s/GPU, $0.25 / $0.11 per million tokens. MI355X is 121% cheaper per token; MI355X delivers 191% more tok/s/GPU.
Around the middle of the 27–95 tok/s/user interactivity band, at 61 tok/s/user on MiniMax M2.5/M2.7: MI300X runs 779 tok/s/GPU at $0.40/M tokens, MI355X runs 1461 at $0.30/M. MI355X is 36% cheaper per token; MI355X delivers 88% more tok/s/GPU.
Setting 78 tok/s/user as the target on MiniMax M2.5/M2.7, MI300X produces 412 tok/s/GPU ($0.75 per million tokens) and MI355X produces 828 ($0.48). MI355X is 54% cheaper per token; MI355X delivers 101% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | MI300X:1248.6MI355X:3637.9 | MI300X:778.8MI355X:1460.9 | MI300X:411.9MI355X:828.3 |
| Cost ($/M tok) | MI300X:$0.250MI355X:$0.113 | MI300X:$0.402MI355X:$0.296 | MI300X:$0.747MI355X:$0.485 |
| tok/s/MW | MI300X:697553MI355X:1372777 | MI300X:435091MI355X:551297 | MI300X:230105MI355X:312550 |
| Concurrency | MI300X:~63MI355X:~256 | MI300X:~26MI355X:~49 | MI300X:~11MI355X:~15 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.