GB200 NVL72 FP4: MTP vs Off Speculative Decoding
Speculative decoding comparison of MTP versus Off on GB200 NVL72 FP4 (NVIDIA Blackwell) running DeepSeek V4 Pro 1.6T. 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.
At 38 tok/s/user on DeepSeek V4 Pro 1.6T (GB200 NVL72 FP4), MTP delivers 9479 tok/s/chip at $0.05 per million tokens; Off delivers 5722 tok/s/chip at $0.09. MTP is 66% cheaper per token; MTP delivers 66% more tok/s/chip. Speculative decoding accepts draft tokens to reduce per-token latency — gains vary by workload and prompt distribution.
MTP posts 9479 tok/s/chip for $0.05 per million tokens at 56 tok/s/user on DeepSeek V4 Pro 1.6T (GB200 NVL72 FP4); Off posts 482 tok/s/chip for $1.07. MTP is 1866% cheaper per token; MTP delivers 1866% more tok/s/chip. Draft-token acceptance rates determine whether speculative decoding helps or hurts at a given concurrency level.
Throughput at 75 tok/s/user on DeepSeek V4 Pro 1.6T (GB200 NVL72 FP4): MTP hits 8616 tok/s/chip, Off hits 188. Per-million costs land at $0.06 and $2.75 respectively. MTP is 4478% cheaper per token; MTP delivers 4478% more tok/s/chip. Speculative decoding trades extra compute on draft tokens for fewer decoding steps — the payoff depends on sequence length and batch size. (Numbers reflect this URL's pinned 8k/1k · fp4 workload — changing sequence or model updates both the table and chart; the table stays pinned to this page's precision, so precision toggles in the controls affect the chart only.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MTP:9478.9Off:5721.7 | MTP:9478.9Off:482.2 | MTP:8615.9Off:188.2 |
| Cost ($/M tok) | MTP:$0.055Off:$0.090 | MTP:$0.055Off:$1.071 | MTP:$0.060Off:$2.745 |
| tok/s/MW | MTP:5068910Off:3059750 | MTP:5068910Off:257871 | MTP:4607427Off:100642 |
| Concurrency | MTP:~16384Off:~1110 | MTP:~16384Off:~54 | MTP:~6302Off:~18 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.