Qwen 3.5 397B-A17B · Performance per dollar

Qwen 3.5 397B-A17B — MI325X vs RTX PRO 6000 performance per dollar

Cost per million tokens of MI325X (AMD CDNA 3) versus RTX PRO 6000 (NVIDIA Blackwell) 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 →

Only MI325X has cost data at 15 tok/s/user on Qwen 3.5 397B-A17B — $0.018 per million tokens. RTX PRO 6000 is unmeasured at this target.

MI325X costs $0.027 per million tokens at 30 tok/s/user on Qwen 3.5 397B-A17B; we have no RTX PRO 6000 benchmark data at this exact target.

At 44 tok/s/user on Qwen 3.5 397B-A17B, MI325X comes in at $0.037 per million tokens. RTX PRO 6000 hasn't been benchmarked at this operating point. (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): MI325X $1.10/chip/hr · RTX PRO 6000 $0.68/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
MI325X$0.018RTX PRO 6000—
MI325X$0.027RTX PRO 6000—
MI325X$0.037RTX PRO 6000—
Concurrency
MI325X~32RTX PRO 6000—
MI325X~21RTX PRO 6000—
MI325X~10RTX PRO 6000—
Qwen 3.5 397B-A17B: MI325X versus RTX PRO 6000 cost per million tokens at matched interactivity levels
MI325X versus RTX PRO 6000 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗