Speed test matrix
INTELLECT-3 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 --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 context21.3K384 ms TTFT
16K context17.8K912 ms TTFT
32K context13.8K2,337 ms TTFT
64K context9,3376,905 ms TTFT
123K context5,81921,270 ms TTFT
128K context5,72022,516 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 | 138.254 ms TTFT | 220.566 ms TTFT | 324.898 ms TTFT | 514.0155 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 133.995 ms TTFT | 213.084 ms TTFT | 314.6138 ms TTFT | 486.9191 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 126.9100 ms TTFT | 200.5130 ms TTFT | 292.6190 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 116.0172 ms TTFT | 177.8202 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 123K | 99.9307 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 | 21.3K | — | 384 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 17.8K | — | 912 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 13.8K | — | 2,337 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 9,337.0 | — | 6,905 ms | — | — | 1 | — | — |
| Prefill | 123K | 1 | Valid | 5,819.0 | — | 21,270 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 5,720.0 | — | 22,516 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 138.2 | 139.0 | 54 ms | 7.2 ms | 1.0 | 1 | 4,145 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 220.5 | 110.4 | 66 ms | 9.1 ms | 2.0 | 0 | 6,618 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 324.8 | 81.3 | 98 ms | 12.3 ms | 4.0 | 0 | 9,748 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 514.0 | 64.5 | 155 ms | 15.5 ms | 8.0 | 0 | 15,416 | 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 | 133.9 | 135.1 | 95 ms | 7.4 ms | 1.0 | 1 | 4,017 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 213.0 | 106.6 | 84 ms | 9.4 ms | 2.0 | 0 | 6,390 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 314.6 | 78.7 | 138 ms | 12.7 ms | 4.0 | 0 | 9,440 | 30.0 s |
| Sustained decode | 16K | 8 | Valid | 486.9 | 61.2 | 191 ms | 16.3 ms | 8.0 | 0 | 14,600 | 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 | 126.9 | 128.8 | 100 ms | 7.8 ms | 1.0 | 1 | 3,807 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 200.5 | 100.4 | 130 ms | 10.0 ms | 2.0 | 0 | 6,014 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 292.6 | 73.3 | 190 ms | 13.6 ms | 4.0 | 0 | 8,776 | 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 | 116.0 | 116.2 | 172 ms | 8.6 ms | 1.0 | 0 | 3,480 | 30.0 s |
| Sustained decode | 64K | 2 | Valid | 177.8 | 89.0 | 202 ms | 11.2 ms | 2.0 | 0 | 5,334 | 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 | 99.9 | 100.1 | 307 ms | 10.0 ms | 1.0 | 0 | 2,999 | 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.