GB200 NVL72 FP4: MTP vs Off Speculative Decoding
Speculative decoding comparison of MTP versus Off on GB200 NVL72 FP4 (NVIDIA Blackwell) running DeepSeek R1. 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 19–175 tok/s/user interactivity band, at 57 tok/s/user on DeepSeek R1 (GB200 NVL72 FP4): MTP runs 11333 tok/s/chip at $0.05/M tokens, Off runs 6442 at $0.08/M. MTP is 76% cheaper per token; MTP delivers 76% more tok/s/chip. Gains from speculative decoding vary by workload; short-output prompts tend to benefit less.
At 97 tok/s/user on DeepSeek R1 (GB200 NVL72 FP4), MTP delivers 7092 tok/s/chip at $0.07 per million tokens; Off delivers 549 tok/s/chip at $0.94. MTP is 1191% cheaper per token; MTP delivers 1191% more tok/s/chip. Speculative decoding accepts draft tokens to reduce per-token latency — gains vary by workload and prompt distribution.
MTP posts 3059 tok/s/chip for $0.17 per million tokens at 136 tok/s/user on DeepSeek R1 (GB200 NVL72 FP4); Off posts 187 tok/s/chip for $2.76. MTP is 1533% cheaper per token; MTP delivers 1533% more tok/s/chip. Draft-token acceptance rates determine whether speculative decoding helps or hurts at a given concurrency level. (Numbers reflect this URL's pinned 1k/1k · fp4 workload — changing sequence or model updates both the table and chart; the table stays pinned to this page's precision, so precision toggles in the controls affect the chart only.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MTP:11333.4Off:6442.0 | MTP:7092.5Off:549.5 | MTP:3058.6Off:187.3 |
| Cost ($/M tok) | MTP:$0.046Off:$0.080 | MTP:$0.073Off:$0.940 | MTP:$0.169Off:$2.758 |
| tok/s/MW | MTP:6060616Off:3444905 | MTP:3792765Off:293833 | MTP:1635620Off:100184 |
| Concurrency | MTP:~3397Off:~3248 | MTP:~2028Off:~130 | MTP:~686Off:~11 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.