B200 BF16: MTP vs Off Speculative Decoding
Speculative decoding comparison of MTP versus Off on B200 BF16 (NVIDIA Blackwell) running Qwen 3.5 397B-A17B. Throughput, cost, and interactivity differences across LLM workloads. Use the chart controls below to switch sequences and metrics — same interactions as the main inference chart.
MTP acceptance-rate implementations differ across inference engines. Points from different engines are not directly comparable on the same curve — throughput and cost at matched interactivity may reflect engine-level differences rather than pure speculative decoding gains. Interpret cross-engine comparisons with caution.
Near the low end of the 103–168 tok/s/user interactivity band, at 119 tok/s/user on Qwen 3.5 397B-A17B (B200 BF16): MTP runs 1058 tok/s/chip at $0.45/M tokens, Off runs 270 at $1.78/M. MTP is 291% cheaper per token; MTP delivers 291% more tok/s/chip. Gains from speculative decoding vary by workload; short-output prompts tend to benefit less.
At 135 tok/s/user on Qwen 3.5 397B-A17B (B200 BF16), MTP delivers 828 tok/s/chip at $0.58 per million tokens; Off delivers 214 tok/s/chip at $2.25. MTP is 288% cheaper per token; MTP delivers 288% more tok/s/chip. Speculative decoding accepts draft tokens to reduce per-token latency — gains vary by workload and prompt distribution.
MTP posts 732 tok/s/chip for $0.66 per million tokens at 152 tok/s/user on Qwen 3.5 397B-A17B (B200 BF16); Off posts 178 tok/s/chip for $2.70. MTP is 312% cheaper per token; MTP delivers 312% more tok/s/chip. Draft-token acceptance rates determine whether speculative decoding helps or hurts at a given concurrency level. (Numbers reflect this URL's pinned 1k/1k · bf16 workload — changing sequence or model updates both the table and chart; the table stays pinned to this page's precision, so precision toggles in the controls affect the chart only.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MTP:1058.2Off:270.4 | MTP:828.2Off:213.6 | MTP:731.8Off:177.8 |
| Cost ($/M tok) | MTP:$0.454Off:$1.777 | MTP:$0.580Off:$2.249 | MTP:$0.657Off:$2.703 |
| tok/s/MW | MTP:618848Off:158129 | MTP:484300Off:124930 | MTP:427931Off:103964 |
| Concurrency | MTP:~40Off:~10 | MTP:~27Off:~7 | MTP:~22Off:~5 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.