Qwen 3.5 397B-A17B · Performance per Dollar

Qwen 3.5 397B-A17B — MI300X vs MI355X Performance per Dollar

Cost per million tokens of MI300X (AMD CDNA 3) versus MI355X (AMD CDNA 4) on Qwen 3.5 397B-A17B. Large-hyperscaler-volume ownership TCO normalized by total tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. 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 →

Push Qwen 3.5 397B-A17B to 73 tok/s/user and MI300X lands at $0.027 per million tokens against MI355X's $0.009 — MI355X costs 67% less.

MI300X: $0.043 per million tokens. MI355X: $0.012. Both at 115 tok/s/user on Qwen 3.5 397B-A17B, with MI355X 73% cheaper.

Toward the upper edge of the 32–198 tok/s/user interactivity band — at 156 tok/s/user — MI300X runs $0.066 per million tokens on Qwen 3.5 397B-A17B while MI355X runs $0.016. MI355X is the cheaper choice by 76%. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

Chip pricing (owning hyperscaler): MI300X $0.95/chip/hr · MI355X $1.50/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

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)
Dollars per Million Tokens
MI300X$0.027MI355X$0.009
MI300X$0.043MI355X$0.012
MI300X$0.066MI355X$0.016
Concurrency
MI300X~20MI355X~46
MI300X~17MI355X~28
MI300X~11MI355X~19
Qwen 3.5 397B-A17B: MI300X versus MI355X cost per million tokens at matched interactivity levels
MI300X versus MI355X cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗