Speed test matrix
Olmo-3-32B-Think 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-3-32B-Think --served-model-name olmo --trust-remote-code --tensor-parallel-size 1 --reasoning-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 context5,582961 ms TTFT
16K context5,3781,967 ms TTFT
32K context5,2264,019 ms TTFT
59K context4,9537,792 ms TTFT
64K context4,9378,477 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 | 19.873 ms TTFT | 40.796 ms TTFT | 80.6124 ms TTFT | 146.8192 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 19.777 ms TTFT | 40.5128 ms TTFT | 79.9185 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 19.5104 ms TTFT | 40.0159 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 59K | 19.2143 ms TTFT | 39.0205 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 | 5,582.0 | — | 961 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 5,378.0 | — | 1,967 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 5,226.0 | — | 4,019 ms | — | — | 1 | — | — |
| Prefill | 59K | 1 | Valid | 4,953.0 | — | 7,792 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 4,937.0 | — | 8,477 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 19.8 | 19.8 | 73 ms | 50.6 ms | 1.0 | 0 | 593 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 40.7 | 20.3 | 96 ms | 49.1 ms | 2.0 | 0 | 1,222 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 80.6 | 20.1 | 124 ms | 49.7 ms | 4.0 | 0 | 2,416 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 146.8 | 18.3 | 192 ms | 54.6 ms | 8.0 | 0 | 4,400 | 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 | 19.7 | 19.7 | 77 ms | 50.8 ms | 1.0 | 0 | 591 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 40.5 | 20.2 | 128 ms | 49.4 ms | 2.0 | 0 | 1,212 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 79.9 | 20.0 | 185 ms | 50.1 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 | 104 ms | 51.3 ms | 1.0 | 0 | 586 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 40.0 | 20.0 | 159 ms | 50.1 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 | 143 ms | 52.0 ms | 1.0 | 0 | 576 | 30.0 s |
| Sustained decode | 59K | 2 | Valid | 39.0 | 19.5 | 205 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.