Speed test matrix
Olmo-3.1-7B-RL-Zero-Math on RTX PRO 6000 Blackwell Server Edition 96GB
vllm · 0.30.1rc1.dev452+g73a583112 · BF164 contexts (8K–59K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 59K, 64K
Hardware
- Type
- Discrete GPU
- GPU
- RTX PRO 6000 Blackwell Server Edition
- VRAM
- 96 GB
- OS
- linux
Engine
- Engine
- vllm
- Version
- 0.30.1rc1.dev452+g73a583112
- Quantization
- BF16
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- cuda-13.2
- Commit
73a5831127a9
Run
- Served model
- olmo
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.7.6
- 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_rtxpro6k-allenai-vllm-73a5831127a9/bin/vllm" serve allenai/Olmo-3.1-7B-RL-Zero-Math --served-model-name olmo --trust-remote-code --tensor-parallel-size 1 --max-model-len 65536 --gpu-memory-utilization 0.83 --host 0.0.0.0 --port 8000 --api-key <redacted> --attention-backend FLASH_ATTN
Prefill
prompt tok/s by context length8K context23.2K233 ms TTFT
16K context22.2K477 ms TTFT
32K context21.1K998 ms TTFT
59K context19.4K1,987 ms TTFT
64K context19.2K2,186 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 | 73.529 ms TTFT | 143.040 ms TTFT | 271.954 ms TTFT | 431.977 ms TTFT | 687.1117 ms TTFT | Over capacity | Over capacity | Over capacity |
| 16K | 68.940 ms TTFT | 134.453 ms TTFT | 257.673 ms TTFT | 398.198 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 61.257 ms TTFT | 119.973 ms TTFT | 232.1100 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 59K | 51.495 ms TTFT | 101.2141 ms TTFT | 198.4172 ms TTFT | 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 | 23.2K | — | 233 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 22.2K | — | 477 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 21.1K | — | 998 ms | — | — | 1 | — | — |
| Prefill | 59K | 1 | Valid | 19.4K | — | 1,987 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 19.2K | — | 2,186 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 73.5 | 73.6 | 29 ms | 13.6 ms | 1.0 | 0 | 2,203 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 143.0 | 71.7 | 40 ms | 14.0 ms | 2.0 | 0 | 4,288 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 271.9 | 68.6 | 54 ms | 14.6 ms | 4.0 | 0 | 8,156 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 431.9 | 54.7 | 77 ms | 18.3 ms | 8.0 | 0 | 12,952 | 30.0 s |
| Sustained decode | 8K | 16 | Valid | 687.1 | 43.8 | 117 ms | 22.8 ms | 16.0 | 0 | 20,608 | 30.0 s |
| Sustained decode | 8K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Valid | 68.9 | 68.9 | 40 ms | 14.5 ms | 1.0 | 0 | 2,065 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 134.4 | 67.4 | 53 ms | 14.8 ms | 2.0 | 0 | 4,030 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 257.6 | 65.0 | 73 ms | 15.4 ms | 4.0 | 0 | 7,728 | 30.0 s |
| Sustained decode | 16K | 8 | Valid | 398.1 | 50.3 | 98 ms | 19.9 ms | 8.0 | 0 | 11,936 | 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 | 61.2 | 61.2 | 57 ms | 16.3 ms | 1.0 | 0 | 1,834 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 119.9 | 60.0 | 73 ms | 16.7 ms | 2.0 | 0 | 3,596 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 232.1 | 58.4 | 100 ms | 17.1 ms | 4.0 | 0 | 6,960 | 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 | 59K | 1 | Valid | 51.4 | 51.5 | 95 ms | 19.4 ms | 1.0 | 0 | 1,543 | 30.0 s |
| Sustained decode | 59K | 2 | Valid | 101.2 | 50.7 | 141 ms | 19.7 ms | 2.0 | 0 | 3,036 | 30.0 s |
| Sustained decode | 59K | 4 | Valid | 198.4 | 49.8 | 172 ms | 20.1 ms | 4.0 | 0 | 5,948 | 30.0 s |
| Sustained decode | 59K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 59K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 59K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 59K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 59K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.