Kimi K2.5/K2.6/K2.7-Code 1T — MI300X vs MI355X
Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) and MI355X (AMD CDNA 4) on Kimi K2.5/K2.6/K2.7-Code 1T. 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 posts 416 tok/s/chip for $0.63 per million tokens at 18 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T; MI355X posts 2256 tok/s/chip for $0.18. MI355X is 243% cheaper per token; MI355X delivers 442% more tok/s/chip.
Throughput at 27 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: MI300X hits 332 tok/s/chip, MI355X hits 1791. Per-million costs land at $0.79 and $0.23 respectively. MI355X is 241% cheaper per token; MI355X delivers 439% more tok/s/chip.
MI300X / MI355X on Kimi K2.5/K2.6/K2.7-Code 1T at 35 tok/s/user: 238 / 1494 tok/s/chip, $1.11 / $0.28 per million tokens. MI355X is 298% cheaper per token; MI355X delivers 528% more tok/s/chip. (Numbers reflect the default 8k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI300X:416.2MI355X:2256.3 | MI300X:332.4MI355X:1790.9 | MI300X:238.0MI355X:1493.9 |
| Cost ($/M tok) | MI300X:$0.634MI355X:$0.185 | MI300X:$0.794MI355X:$0.233 | MI300X:$1.109MI355X:$0.279 |
| tok/s/MW | MI300X:299416MI355X:1079552 | MI300X:239149MI355X:856871 | MI300X:171207MI355X:714775 |
| Concurrency | MI300X:~21MI355X:~56 | MI300X:~11MI355X:~31 | MI300X:~6MI355X:~20 |
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
Kimi K2.5/2.6/2.7-Code 1T • 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