Speed test matrix
gemma-4-12B-it on RTX PRO 6000 Blackwell Server Edition 96GB
vllm · 0.30.1rc1.dev452+g73a583112 · BF166 contexts (8K–251K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 128K, 251K, 256K
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
- gemma
- 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-google-vllm-73a5831127a9/bin/vllm" serve google/gemma-4-12B-it --served-model-name gemma --trust-remote-code --tensor-parallel-size 1 --reasoning-parser gemma4 --enable-auto-tool-choice --tool-call-parser gemma4 --max-model-len 262144 --gpu-memory-utilization 0.83 --host 0.0.0.0 --port 8000 --api-key <redacted> --attention-backend TRITON_ATTN
Prefill
prompt tok/s by context length8K context11K745 ms TTFT
16K context9,8261,655 ms TTFT
32K context7,7674,168 ms TTFT
64K context5,41211,929 ms TTFT
128K context3,36938,290 ms TTFT
251K context1,937130,497 ms TTFT
256K context1,904135,428 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 | 51.051 ms TTFT | Looped | Looped | Looped | Looped | Looped | Looped | Over capacity |
| 16K | Looped | 96.8111 ms TTFT | Looped | Looped | Looped | Looped | Looped | Over capacity |
| 32K | 45.8118 ms TTFT | 91.3171 ms TTFT | Looped | Looped | Looped | 719.3935 ms TTFT | Over capacity | Over capacity |
| 64K | 42.4215 ms TTFT | Looped | 169.0419 ms TTFT | Looped | Looped | Over capacity | Over capacity | Over capacity |
| 128K | Looped | 73.9661 ms TTFT | 147.3978 ms TTFT | 275.31,653 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 251K | 29.71,081 ms TTFT | 59.41,505 ms TTFT | 118.62,276 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Looped: the model kept repeating the same text, so the benchmark discarded this measurement. 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 | 11K | — | 745 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 9,826.0 | — | 1,655 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 7,767.0 | — | 4,168 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 5,412.0 | — | 11,929 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 3,369.0 | — | 38,290 ms | — | — | 1 | — | — |
| Prefill | 251K | 1 | Valid | 1,937.0 | — | 130,497 ms | — | — | 1 | — | — |
| Prefill | 256K | 1 | Valid | 1,904.0 | — | 135,428 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 51.0 | 51.0 | 51 ms | 19.6 ms | 1.0 | 0 | 1,529 | 30.0 s |
| Sustained decode | 8K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 32 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 64 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 8K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 2 | Valid | 96.8 | 48.5 | 111 ms | 20.6 ms | 2.0 | 0 | 2,902 | 30.0 s |
| Sustained decode | 16K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 32 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 64 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 1 | Valid | 45.8 | 45.8 | 118 ms | 21.8 ms | 1.0 | 0 | 1,373 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 91.3 | 45.7 | 171 ms | 21.9 ms | 2.0 | 0 | 2,738 | 30.0 s |
| Sustained decode | 32K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 32K | 32 | Valid | 719.3 | 22.6 | 935 ms | 44.3 ms | 32.0 | 0 | 21,588 | 30.0 s |
| Sustained decode | 32K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 32K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 1 | Valid | 42.4 | 42.4 | 215 ms | 23.6 ms | 1.0 | 0 | 1,272 | 30.0 s |
| Sustained decode | 64K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 4 | Valid | 169.0 | 42.2 | 419 ms | 23.7 ms | 4.0 | 0 | 5,071 | 30.0 s |
| Sustained decode | 64K | 8 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 16 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 64K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 128K | 2 | Valid | 73.9 | 37.0 | 661 ms | 27.0 ms | 2.0 | 0 | 2,216 | 30.0 s |
| Sustained decode | 128K | 4 | Valid | 147.3 | 36.8 | 978 ms | 27.2 ms | 4.0 | 0 | 4,418 | 30.0 s |
| Sustained decode | 128K | 8 | Valid | 275.3 | 34.3 | 1,653 ms | 29.2 ms | 8.0 | 0 | 8,259 | 30.0 s |
| Sustained decode | 128K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 1 | Valid | 29.7 | 29.8 | 1,081 ms | 33.6 ms | 1.0 | 0 | 890 | 30.0 s |
| Sustained decode | 251K | 2 | Valid | 59.4 | 29.8 | 1,505 ms | 33.6 ms | 2.0 | 0 | 1,782 | 30.0 s |
| Sustained decode | 251K | 4 | Valid | 118.6 | 29.6 | 2,276 ms | 33.8 ms | 4.0 | 0 | 3,556 | 30.0 s |
| Sustained decode | 251K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 251K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Looped: the model kept repeating the same text, so the benchmark discarded this measurement. Over capacity: not run because this many requests at this context would exceed the server's KV cache.