Qwen 3.5 397B-A17B · Performance per Dollar

Qwen 3.5 397B-A17B — H100 vs MI355X Performance per Dollar

Cost per million tokens of H100 (NVIDIA Hopper) 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 →

Near the low end of the 32–228 tok/s/user interactivity band — at 81 tok/s/user — H100 runs $0.054 per million tokens on Qwen 3.5 397B-A17B while MI355X runs $0.009. MI355X is the cheaper choice by 83%.

On Qwen 3.5 397B-A17B at 130 tok/s/user, the per-million math comes out to $0.096 for H100 and $0.013 for MI355X; MI355X delivers 7.3× the total tokens per dollar.

At 179 tok/s/user on Qwen 3.5 397B-A17B, H100 costs $0.13 per million tokens; MI355X costs $0.019. MI355X delivers 6.9× the tokens per dollar 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): H100 $1.17/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
H100$0.054MI355X$0.009
H100$0.096MI355X$0.013
H100$0.13MI355X$0.019
Concurrency
H100~12MI355X~44
H100~6MI355X~23
H100~4MI355X~14
Qwen 3.5 397B-A17B: H100 versus MI355X cost per million tokens at matched interactivity levels
H100 versus MI355X cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗