Qwen 3.5 397B-A17B · Performance per Dollar

Qwen 3.5 397B-A17B — B300 vs MI300X Performance per Dollar

Cost per million tokens of B300 (NVIDIA Blackwell) versus MI300X (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 →

Near the low end of the 18–198 tok/s/user interactivity band — at 63 tok/s/user — B300 runs $0.011 per million tokens on Qwen 3.5 397B-A17B while MI300X runs $0.024. B300 is the cheaper choice by 55%.

On Qwen 3.5 397B-A17B at 108 tok/s/user, the per-million math comes out to $0.013 for B300 and $0.040 for MI300X; B300 delivers 3.0× the total tokens per dollar.

At 153 tok/s/user on Qwen 3.5 397B-A17B, B300 costs $0.021 per million tokens; MI300X costs $0.064. B300 delivers 3.1× 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): B300 $2.26/chip/hr · MI300X $0.95/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
B300$0.011MI300X$0.024
B300$0.013MI300X$0.040
B300$0.021MI300X$0.064
Concurrency
B300~56MI300X~20
B300~44MI300X~18
B300~22MI300X~12
Qwen 3.5 397B-A17B: B300 versus MI300X cost per million tokens at matched interactivity levels
B300 versus MI300X cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗