Llama 3.3 70B — H200 vs MI355X
Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and MI355X (AMD CDNA 4) on Llama 3.3 70B. 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.
Throughput at 37 tok/s/user on Llama 3.3 70B: H200 hits 3361 tok/s/chip, MI355X hits 4326. Per-million costs land at $0.10 and $0.10 respectively. MI355X is 5% cheaper per token; MI355X delivers 29% more tok/s/chip.
H200 / MI355X on Llama 3.3 70B at 61 tok/s/user: 2424 / 2613 tok/s/chip, $0.14 / $0.16 per million tokens. H200 is 14% cheaper per token; MI355X delivers 8% more tok/s/chip.
Toward the upper edge of the 14–108 tok/s/user interactivity band, at 85 tok/s/user on Llama 3.3 70B: H200 runs 1644 tok/s/chip at $0.21/M tokens, MI355X runs 1060 at $0.39/M. H200 is 91% cheaper per token; H200 delivers 55% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H200:3361.5MI355X:4326.2 | H200:2423.7MI355X:2612.5 | H200:1644.2MI355X:1059.7 |
| Cost ($/M tok) | H200:$0.101MI355X:$0.096 | H200:$0.140MI355X:$0.159 | H200:$0.206MI355X:$0.393 |
| tok/s/MW | H200:2453643MI355X:2069965 | H200:1769138MI355X:1250014 | H200:1200156MI355X:507051 |
| Concurrency | H200:~32MI355X:~18 | H200:~20MI355X:~22 | H200:~8MI355X:~6 |
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
Llama 3.3 70B Instruct • 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