Qwen 3.5 397B-A17B · Performance per dollar

Qwen 3.5 397B-A17B — MI355X vs TPU7x performance per dollar

Cost per million tokens of MI355X (AMD CDNA 4) versus TPU7x (Google Ironwood) 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 →

MI355X: $0.015 per million tokens. TPU7x: $0.004. Both at 151 tok/s/user on Qwen 3.5 397B-A17B, with TPU7x 72% cheaper.

Around the middle of the 82–359 tok/s/user interactivity band — at 220 tok/s/user — MI355X runs $0.029 per million tokens on Qwen 3.5 397B-A17B while TPU7x runs $0.005. TPU7x is the cheaper choice by 82%.

On Qwen 3.5 397B-A17B at 290 tok/s/user, the per-million math comes out to $0.071 for MI355X and $0.006 for TPU7x; TPU7x delivers 12× the total tokens per dollar. (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): MI355X $1.50/chip/hr · TPU7x $1.03/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
MI355X$0.015TPU7x$0.004
MI355X$0.029TPU7x$0.005
MI355X$0.071TPU7x$0.006
Concurrency
MI355X~20TPU7x~496
MI355X~10TPU7x~367
MI355X~3TPU7x~253
Qwen 3.5 397B-A17B: MI355X versus TPU7x cost per million tokens at matched interactivity levels
MI355X versus TPU7x cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗