Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) and MI355X (AMD CDNA 4) on Qwen 3.5 397B-A17B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics β 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 β
MI300X / MI355X on Qwen 3.5 397B-A17B at 81 tok/s/user: 713 / 42087 tok/s/chip, $0.37 / $0.01 per million tokens. MI355X is 3640% cheaper per token; MI355X delivers 5806% more tok/s/chip.
Around the middle of the 4β314 tok/s/user interactivity band, at 159 tok/s/user on Qwen 3.5 397B-A17B: MI300X runs 713 tok/s/chip at $0.37/M tokens, MI355X runs 21701 at $0.02/M. MI355X is 1829% cheaper per token; MI355X delivers 2945% more tok/s/chip.
Setting 237 tok/s/user as the target on Qwen 3.5 397B-A17B, MI300X produces 713 tok/s/chip ($0.37 per million tokens) and MI355X produces 6279 ($0.07). MI355X is 458% cheaper per token; MI355X delivers 781% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp8 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI300X:712.6MI355X:42086.8 | MI300X:712.6MI355X:21700.6 | MI300X:712.6MI355X:6278.7 |
| Cost ($/M tok) | MI300X:$0.370MI355X:$0.010 | MI300X:$0.370MI355X:$0.019 | MI300X:$0.370MI355X:$0.066 |
| tok/s/MW | MI300X:512683MI355X:20137246 | MI300X:512683MI355X:10383053 | MI300X:512683MI355X:3004153 |
| Concurrency | MI300X:~4MI355X:~40 | MI300X:~4MI355X:~16 | MI300X:~4MI355X:~4 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
TCO $/chip/hr:
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.
Matching measurements exist, but their chip series are hidden.
Shift+Scroll to zoom β’ Drag to pan β’ Double-click to reset β’ Click a point to pin tooltip
1 The ATOM engine is promising, however it has yet to serve production tokens. It is still in its infant stage.
Qwen3.5 397B 8K / 1K Total Tokens per $1 TCO vs. Interactivity