Kimi K2.5/K2.6/K2.7-Code 1T · Chip comparison

Kimi K2.5/K2.6/K2.7-Code 1T — H200 vs MI300X

Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and MI300X (AMD CDNA 3) 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.

Near the low end of the 17–43 tok/s/user interactivity band, at 23 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: H200 runs 1,074 tok/s/chip at $0.32 per million tokens, MI300X runs 386 at $0.68. H200 is 54% cheaper per token; H200 delivers 178% more tok/s/chip.

Setting 30 tok/s/user as the target on Kimi K2.5/K2.6/K2.7-Code 1T, H200 produces 974 tok/s/chip ($0.35 per million tokens) and MI300X produces 289 ($0.91). H200 is 62% cheaper per token; H200 delivers 3.4× the tok/s/chip.

At 37 tok/s/user interactivity on Kimi K2.5/K2.6/K2.7-Code 1T, H200 delivers 896 tok/s/chip at $0.38 per million tokens; MI300X delivers 224 tok/s/chip at $1.18. H200 is 68% cheaper per token; H200 delivers 4.0× the tok/s/chip at this point. (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.)

View performance per dollar →

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)
H2001,074MI300X386
H200974MI300X289
H200896MI300X224
Cost ($/M tok)
H200$0.32MI300X$0.68
H200$0.35MI300X$0.91
H200$0.38MI300X$1.18
tok/s/MW
H200783,946MI300X277,903
H200710,611MI300X207,727
H200654,072MI300X160,804
Concurrency
H200~45MI300X~16
H200~30MI300X~9
H200~22MI300X~5