Qwen 3.5 397B-A17B · Performance per Dollar

Qwen 3.5 397B-A17B — H100 vs MI325X Performance per Dollar

Cost per million tokens of H100 (NVIDIA Hopper) 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 →

MI325X edges H100 at 28 tok/s/user on Qwen 3.5 397B-A17B — $0.026 per million tokens versus $0.054, a 51% lower cost per token.

Push Qwen 3.5 397B-A17B to 38 tok/s/user and H100 lands at $0.054 per million tokens against MI325X's $0.032 — MI325X costs 41% less.

H100: $0.054 per million tokens. MI325X: $0.041. Both at 48 tok/s/user on Qwen 3.5 397B-A17B, with MI325X 24% 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): H100 $1.17/chip/hr · MI325X $1.10/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
H100$0.054MI325X$0.026
H100$0.054MI325X$0.032
H100$0.054MI325X$0.041
Concurrency
H100~12MI325X~17
H100~12MI325X~20
H100~12MI325X~8
Qwen 3.5 397B-A17B: H100 versus MI325X cost per million tokens at matched interactivity levels
H100 versus MI325X cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗