Qwen 3.5 397B-A17B · Performance per dollar
Qwen 3.5 397B-A17B — GB300 NVL72 vs MI325X performance per dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) 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 →
GB300 NVL72 edges MI325X at 146 tok/s/user on Qwen 3.5 397B-A17B — $0.011 per million tokens versus $0.053, a 384% cost-per-token gap.
Push Qwen 3.5 397B-A17B to 291 tok/s/user and GB300 NVL72 lands at $0.026 per million tokens against MI325X's $0.053 — GB300 NVL72 pulls ahead by 105%.
GB300 NVL72: $0.046 per million tokens. MI325X: $0.053. Both at 436 tok/s/user on Qwen 3.5 397B-A17B, with GB300 NVL72 16% cheaper. (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): GB300 NVL72 $2.31/chip/hr · MI325X $1.10/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
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 | GB300 NVL72$0.011MI325X$0.053 | GB300 NVL72$0.026MI325X$0.053 | GB300 NVL72$0.046MI325X$0.053 |
| Concurrency | GB300 NVL72~370MI325X~12 | GB300 NVL72~112MI325X~12 | GB300 NVL72~53MI325X~12 |