MiniMax M2.5/M2.7 — B300 vs MI300X
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI300X (AMD CDNA 3) 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.
B300 posts 13508 tok/s/chip for $0.05 per million tokens at 31 tok/s/user on MiniMax M2.5/M2.7; MI300X posts 1563 tok/s/chip for $0.17. B300 is 263% cheaper per token; B300 delivers 764% more tok/s/chip.
Throughput at 49 tok/s/user on MiniMax M2.5/M2.7: B300 hits 8734 tok/s/chip, MI300X hits 1396. Per-million costs land at $0.07 and $0.19 respectively. B300 is 163% cheaper per token; B300 delivers 525% more tok/s/chip.
B300 / MI300X on MiniMax M2.5/M2.7 at 67 tok/s/user: 5346 / 1067 tok/s/chip, $0.12 / $0.25 per million tokens. B300 is 111% cheaper per token; B300 delivers 401% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:13508.2MI300X:1563.4 | B300:8733.6MI300X:1396.3 | B300:5345.6MI300X:1066.7 |
| Cost ($/M tok) | B300:$0.046MI300X:$0.169 | B300:$0.072MI300X:$0.189 | B300:$0.117MI300X:$0.247 |
| tok/s/MW | B300:7109570MI300X:1124722 | B300:4596631MI300X:1004511 | B300:2813494MI300X:767436 |
| Concurrency | B300:~1929MI300X:~18 | B300:~128MI300X:~6 | B300:~23MI300X:~4 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
MiniMax M2.5/2.7 230B • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip