Speed test matrix
Olmo-3.1-32B-Instruct-SFT on RTX PRO 6000 Blackwell Server Edition 96GB
vllm · 0.30.1rc1.dev151+g73a78e6f1 · 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.dev151+g73a78e6f1
- Quantization
- BF16
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- cuda-13.2
- Commit
73a78e6f1f38
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-73a78e6f1f38/bin/vllm" serve allenai/Olmo-3.1-32B-Instruct-SFT --served-model-name olmo --trust-remote-code --tensor-parallel-size 1 --enable-auto-tool-choice --tool-call-parser olmo3 --max-model-len 65536 --gpu-memory-utilization 0.84 --host 0.0.0.0 --port 8000 --api-key <redacted> --attention-backend FLASH_ATTN
Prefill
prompt tok/s by context length8K context5,599961 ms TTFT
16K context5,3971,962 ms TTFT
32K context5,2394,011 ms TTFT
59K context4,9777,755 ms TTFT
64K context4,9368,481 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 | 19.872 ms TTFT | 40.793 ms TTFT | 80.6146 ms TTFT | 146.7191 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 19.779 ms TTFT | 40.5104 ms TTFT | 80.0162 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 19.598 ms TTFT | 40.0151 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 59K | 19.2130 ms TTFT | 39.0191 ms TTFT | 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 | 5,599.0 | — | 961 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 5,397.0 | — | 1,962 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 5,239.0 | — | 4,011 ms | — | — | 1 | — | — |
| Prefill | 59K | 1 | Valid | 4,977.0 | — | 7,755 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 4,936.0 | — | 8,481 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 19.8 | 19.8 | 72 ms | 50.5 ms | 1.0 | 0 | 594 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 40.7 | 20.4 | 93 ms | 49.1 ms | 2.0 | 0 | 1,220 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 80.6 | 20.1 | 146 ms | 49.6 ms | 4.0 | 0 | 2,416 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 146.7 | 18.3 | 191 ms | 54.6 ms | 8.0 | 0 | 4,392 | 29.9 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 | 19.7 | 19.7 | 79 ms | 50.8 ms | 1.0 | 0 | 590 | 29.9 s |
| Sustained decode | 16K | 2 | Valid | 40.5 | 20.2 | 104 ms | 49.4 ms | 2.0 | 0 | 1,214 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 80.0 | 20.0 | 162 ms | 50.0 ms | 4.0 | 0 | 2,396 | 30.0 s |
| Sustained decode | 16K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 19.5 | 19.5 | 98 ms | 51.2 ms | 1.0 | 0 | 585 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 40.0 | 20.0 | 151 ms | 50.0 ms | 2.0 | 0 | 1,198 | 30.0 s |
| Sustained decode | 32K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 19.2 | 19.2 | 130 ms | 52.0 ms | 1.0 | 0 | 577 | 30.0 s |
| Sustained decode | 59K | 2 | Valid | 39.0 | 19.5 | 191 ms | 51.3 ms | 2.0 | 0 | 1,170 | 30.0 s |
| Sustained decode | 59K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| 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.