Kimi K3 2.8T · Chip comparison
Kimi K3 2.8T — H200 vs MI355X
Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and MI355X (AMD CDNA 4) on Kimi K3 2.8T. 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Near the low end of the 2–211 tok/s/user interactivity band, at 54 tok/s/user on Kimi K3 2.8T: H200 runs 70 tok/s/chip at $4.85 per million tokens, MI355X runs 9,298 at $0.045. MI355X is 99% cheaper per token; MI355X delivers 133× the tok/s/chip.
Setting 107 tok/s/user as the target on Kimi K3 2.8T, H200 produces 70 tok/s/chip ($4.85 per million tokens) and MI355X produces 4,722 ($0.088). MI355X is 98% cheaper per token; MI355X delivers 68× the tok/s/chip.
At 159 tok/s/user interactivity on Kimi K3 2.8T, H200 delivers 70 tok/s/chip at $4.85 per million tokens; MI355X delivers 2,762 tok/s/chip at $0.15. MI355X is 97% cheaper per token; MI355X delivers 40× the tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H20070MI355X9,298 | H20070MI355X4,722 | H20070MI355X2,762 |
| Cost ($/M tok) | H200$4.85MI355X$0.045 | H200$4.85MI355X$0.088 | H200$4.85MI355X$0.15 |
| tok/s/MW | H20051,001MI355X4,448,807 | H20051,001MI355X2,259,555 | H20051,001MI355X1,321,660 |
| Concurrency | H200~1MI355X~23 | H200~1MI355X~24 | H200~1MI355X~4 |