Speed test matrix
INTELLECT-3.1 on H200 NVL 141GB ×2
vllm · 0.26.1rc1.dev638+g52be12cfa · BF165 contexts (8K–123K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 123K, 128K
Hardware
- Type
- Discrete GPU
- GPU
- H200 NVL
- GPU count
- 2
- VRAM
- 282 GB (2 × 141 GB)
- OS
- linux
Engine
- Engine
- vllm
- Version
- 0.26.1rc1.dev638+g52be12cfa
- Quantization
- BF16
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- cuda-13.2
- Commit
52be12cfac0c
Run
- Served model
- intellect
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.4.29
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 4,096 tokens
Launch command
"$HOME/env_h200-primeintellect-vllm/bin/vllm" serve PrimeIntellect/INTELLECT-3.1 --served-model-name intellect --tensor-parallel-size 2 --reasoning-parser deepseek_r1 --enable-auto-tool-choice --tool-call-parser qwen3_coder --max-model-len 131072 --gpu-memory-utilization 0.873168 --host 0.0.0.0 --port 8000 --api-key <redacted>
Prefill
prompt tok/s by context length8K context20.8K394 ms TTFT
16K context18K903 ms TTFT
32K context13.7K2,361 ms TTFT
64K context9,3786,874 ms TTFT
123K context5,81921,271 ms TTFT
128K context5,63422,859 ms TTFT
Sustained decode
total tok/s · rows are context length, columns are simultaneous requests| Context | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 |
|---|---|---|---|---|---|---|---|---|
| 8K | 138.650 ms TTFT | 220.952 ms TTFT | 326.579 ms TTFT | 516.6140 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 134.289 ms TTFT | 213.089 ms TTFT | 314.8140 ms TTFT | 490.1195 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 127.1121 ms TTFT | 200.8149 ms TTFT | 293.7222 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 116.2141 ms TTFT | 178.1237 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 123K | 100.2278 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.
TTFT is measured after the benchmark warms the server's prompt cache, so it mostly excludes prefill.
All measurements
Latencies are medians. Total tok/s is output across all simultaneous requests.| Phase | Context | Requests at once | Status | Total tok/s | Per request tok/s | TTFT | Time between tokens | Average active requests | Completed requests | Output tokens | Measured for |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Prefill | 8K | 1 | Valid | 20.8K | — | 394 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 18K | — | 903 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 13.7K | — | 2,361 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 9,378.0 | — | 6,874 ms | — | — | 1 | — | — |
| Prefill | 123K | 1 | Valid | 5,819.0 | — | 21,271 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 5,634.0 | — | 22,859 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 138.6 | 139.5 | 50 ms | 7.2 ms | 1.0 | 1 | 4,157 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 220.9 | 110.6 | 52 ms | 9.0 ms | 2.0 | 0 | 6,626 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 326.5 | 81.8 | 79 ms | 12.2 ms | 4.0 | 0 | 9,792 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 516.6 | 64.9 | 140 ms | 15.4 ms | 8.0 | 0 | 15,496 | 30.0 s |
| Sustained decode | 8K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Valid | 134.2 | 135.4 | 89 ms | 7.4 ms | 1.0 | 1 | 4,025 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 213.0 | 106.7 | 89 ms | 9.4 ms | 2.0 | 0 | 6,392 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 314.8 | 78.8 | 140 ms | 12.7 ms | 4.0 | 0 | 9,440 | 30.0 s |
| Sustained decode | 16K | 8 | Valid | 490.1 | 61.6 | 195 ms | 16.2 ms | 8.0 | 0 | 14,704 | 30.0 s |
| Sustained decode | 16K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 1 | Valid | 127.1 | 129.5 | 121 ms | 7.7 ms | 1.0 | 1 | 3,814 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 200.8 | 100.6 | 149 ms | 9.9 ms | 2.0 | 0 | 6,024 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 293.7 | 73.6 | 222 ms | 13.6 ms | 4.0 | 0 | 8,808 | 30.0 s |
| Sustained decode | 32K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 1 | Valid | 116.2 | 116.4 | 141 ms | 8.6 ms | 1.0 | 0 | 3,486 | 30.0 s |
| Sustained decode | 64K | 2 | Valid | 178.1 | 89.3 | 237 ms | 11.2 ms | 2.0 | 0 | 5,342 | 30.0 s |
| Sustained decode | 64K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 1 | Valid | 100.2 | 100.4 | 278 ms | 10.0 ms | 1.0 | 0 | 3,006 | 30.0 s |
| Sustained decode | 123K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.