Kimi K2.5/K2.6/K2.7-Code 1T · Chip comparison
Kimi K2.5/K2.6/K2.7-Code 1T — B300 vs MI355X
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) 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.
B300 / MI355X on Kimi K2.5/K2.6/K2.7-Code 1T at 38 tok/s/user: 4,317 / 4,004 tok/s/chip, $0.15 / $0.10 per million tokens. MI355X is 28% cheaper per token; B300 delivers 8% more tok/s/chip.
Around the middle of the 11–123 tok/s/user interactivity band, at 67 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: B300 runs 2,747 tok/s/chip at $0.23 per million tokens, MI355X runs 2,493 at $0.17. MI355X is 27% cheaper per token; B300 delivers 10% more tok/s/chip.
Setting 95 tok/s/user as the target on Kimi K2.5/K2.6/K2.7-Code 1T, B300 produces 1,848 tok/s/chip ($0.34 per million tokens) and MI355X produces 1,739 ($0.24). MI355X is 29% cheaper per token; B300 delivers 6% more tok/s/chip. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B3004,317MI355X4,004 | B3002,747MI355X2,493 | B3001,848MI355X1,739 |
| Cost ($/M tok) | B300$0.15MI355X$0.10 | B300$0.23MI355X$0.17 | B300$0.34MI355X$0.24 |
| tok/s/MW | B3002,272,062MI355X1,915,595 | B3001,445,598MI355X1,192,676 | B300972,471MI355X831,906 |
| Concurrency | B300~51MI355X~102 | B300~19MI355X~17 | B300~9MI355X~9 |