Speed test matrix
Olmo-3.1-7B-RL-Zero-Code 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-Code --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 context23.1K233 ms TTFT
16K context22.3K475 ms TTFT
32K context21K999 ms TTFT
59K context19.4K1,988 ms TTFT
64K context19.2K2,185 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 | 73.330 ms TTFT | 142.838 ms TTFT | 271.752 ms TTFT | 431.373 ms TTFT | 686.4113 ms TTFT | Over capacity | Over capacity | Over capacity |
| 16K | 68.739 ms TTFT | 134.353 ms TTFT | 257.372 ms TTFT | 397.7100 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 61.056 ms TTFT | 119.774 ms TTFT | 231.7102 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 59K | 51.390 ms TTFT | 101.1119 ms TTFT | 198.0177 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 | 23.1K | — | 233 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 22.3K | — | 475 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 21K | — | 999 ms | — | — | 1 | — | — |
| Prefill | 59K | 1 | Valid | 19.4K | — | 1,988 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 19.2K | — | 2,185 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 73.3 | 73.5 | 30 ms | 13.6 ms | 1.0 | 0 | 2,200 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 142.8 | 71.6 | 38 ms | 14.0 ms | 2.0 | 0 | 4,283 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 271.7 | 68.6 | 52 ms | 14.6 ms | 4.0 | 0 | 8,148 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 431.3 | 54.6 | 73 ms | 18.3 ms | 8.0 | 0 | 12,936 | 30.0 s |
| Sustained decode | 8K | 16 | Valid | 686.4 | 43.7 | 113 ms | 22.9 ms | 16.0 | 0 | 20,576 | 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 | 39 ms | 14.5 ms | 1.0 | 0 | 2,061 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 134.3 | 67.3 | 53 ms | 14.9 ms | 2.0 | 0 | 4,028 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 257.3 | 64.9 | 72 ms | 15.4 ms | 4.0 | 0 | 7,720 | 30.0 s |
| Sustained decode | 16K | 8 | Valid | 397.7 | 50.2 | 100 ms | 19.9 ms | 8.0 | 0 | 11,928 | 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 | 56 ms | 16.4 ms | 1.0 | 0 | 1,831 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 119.7 | 60.0 | 74 ms | 16.7 ms | 2.0 | 0 | 3,590 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 231.7 | 58.3 | 102 ms | 17.2 ms | 4.0 | 0 | 6,952 | 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 | 90 ms | 19.5 ms | 1.0 | 0 | 1,539 | 30.0 s |
| Sustained decode | 59K | 2 | Valid | 101.1 | 50.6 | 119 ms | 19.7 ms | 2.0 | 0 | 3,034 | 30.0 s |
| Sustained decode | 59K | 4 | Valid | 198.0 | 49.8 | 177 ms | 20.1 ms | 4.0 | 0 | 5,940 | 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.