Speed test matrix
Olmo-3-7B-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-3-7B-Think --served-model-name olmo --trust-remote-code --tensor-parallel-size 1 --reasoning-parser olmo3 --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 context22.9K237 ms TTFT
16K context22.1K480 ms TTFT
32K context20.8K1,014 ms TTFT
59K context19.3K2,005 ms TTFT
64K context19.1K2,199 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 | 73.233 ms TTFT | 142.640 ms TTFT | 271.357 ms TTFT | 431.771 ms TTFT | 686.0118 ms TTFT | Over capacity | Over capacity | Over capacity |
| 16K | 68.741 ms TTFT | 134.157 ms TTFT | 256.677 ms TTFT | 396.7109 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 61.062 ms TTFT | 119.681 ms TTFT | 231.4118 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 59K | 51.3106 ms TTFT | 101.1136 ms TTFT | 197.8186 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 | 22.9K | — | 237 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 22.1K | — | 480 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 20.8K | — | 1,014 ms | — | — | 1 | — | — |
| Prefill | 59K | 1 | Valid | 19.3K | — | 2,005 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 19.1K | — | 2,199 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 73.2 | 73.4 | 33 ms | 13.6 ms | 1.0 | 0 | 2,196 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 142.6 | 71.5 | 40 ms | 14.0 ms | 2.0 | 0 | 4,276 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 271.3 | 68.5 | 57 ms | 14.6 ms | 4.0 | 0 | 8,139 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 431.7 | 54.6 | 71 ms | 18.3 ms | 8.0 | 0 | 12,944 | 30.0 s |
| Sustained decode | 8K | 16 | Valid | 686.0 | 43.7 | 118 ms | 22.9 ms | 16.0 | 0 | 20,577 | 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 | 68.7 | 68.8 | 41 ms | 14.5 ms | 1.0 | 0 | 2,060 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 134.1 | 67.2 | 57 ms | 14.9 ms | 2.0 | 0 | 4,022 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 256.6 | 64.7 | 77 ms | 15.5 ms | 4.0 | 0 | 7,696 | 30.0 s |
| Sustained decode | 16K | 8 | Valid | 396.7 | 50.1 | 109 ms | 20.0 ms | 8.0 | 0 | 11,896 | 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 | 61.0 | 61.1 | 62 ms | 16.4 ms | 1.0 | 0 | 1,830 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 119.6 | 59.9 | 81 ms | 16.7 ms | 2.0 | 0 | 3,588 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 231.4 | 58.2 | 118 ms | 17.2 ms | 4.0 | 0 | 6,940 | 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 | 51.3 | 51.4 | 106 ms | 19.5 ms | 1.0 | 0 | 1,540 | 30.0 s |
| Sustained decode | 59K | 2 | Valid | 101.1 | 50.6 | 136 ms | 19.8 ms | 2.0 | 0 | 3,032 | 30.0 s |
| Sustained decode | 59K | 4 | Valid | 197.8 | 49.7 | 186 ms | 20.1 ms | 4.0 | 0 | 5,933 | 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.