Speed test matrix
gpt-oss-120b on RTX PRO 6000 Blackwell Server Edition 96GB
vllm · 0.30.1rc1.dev452+g73a583112 · MXFP45 contexts (8K–123K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 123K, 128K
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
- MXFP4
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- cuda-13.2
- Commit
73a5831127a9
Run
- Served model
- gpt-oss
- 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
env MAX_JOBS=2 FLASHINFER_NVCC_THREADS=1 TORCHINDUCTOR_COMPILE_THREADS=1 "$HOME/env_rtxpro6k-openai-vllm-73a5831127a9/bin/vllm" serve openai/gpt-oss-120b --served-model-name gpt-oss --trust-remote-code --tensor-parallel-size 1 --enable-auto-tool-choice --tool-call-parser openai --max-model-len 131072 --gpu-memory-utilization 0.82 --host 0.0.0.0 --port 8000 --api-key <redacted> --attention-backend FLASHINFER --moe-backend marlin
Prefill
prompt tok/s by context length8K context23.8K343 ms TTFT
16K context22.5K720 ms TTFT
32K context19.6K1,641 ms TTFT
64K context15.4K4,155 ms TTFT
123K context11K11,191 ms TTFT
128K context10.7K11,914 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 | 179.044 ms TTFT | 266.555 ms TTFT | 401.983 ms TTFT | 579.1113 ms TTFT | 838.8194 ms TTFT | Over capacity | Over capacity | Over capacity |
| 16K | 172.250 ms TTFT | 269.566 ms TTFT | 395.3103 ms TTFT | 511.3172 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 171.557 ms TTFT | 241.397 ms TTFT | 383.7153 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 145.391 ms TTFT | 220.3159 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 123K | 116.3147 ms TTFT | Over capacity | 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 | 23.8K | — | 343 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 22.5K | — | 720 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 19.6K | — | 1,641 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 15.4K | — | 4,155 ms | — | — | 1 | — | — |
| Prefill | 123K | 1 | Valid | 11K | — | 11,191 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 10.7K | — | 11,914 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 179.0 | 179.7 | 44 ms | 5.6 ms | 1.0 | 1 | 5,364 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 266.5 | 135.9 | 55 ms | 7.4 ms | 2.0 | 2 | 7,996 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 401.9 | 101.1 | 83 ms | 9.9 ms | 4.0 | 0 | 12,054 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 579.1 | 74.8 | 113 ms | 13.4 ms | 8.0 | 0 | 17,372 | 30.0 s |
| Sustained decode | 8K | 16 | Valid | 838.8 | 54.2 | 194 ms | 18.5 ms | 16.0 | 0 | 25,153 | 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 | 172.2 | 172.9 | 50 ms | 5.8 ms | 1.0 | 1 | 5,165 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 269.5 | 132.8 | 66 ms | 7.5 ms | 2.0 | 2 | 8,084 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 395.3 | 97.7 | 103 ms | 10.2 ms | 4.0 | 0 | 11,855 | 30.0 s |
| Sustained decode | 16K | 8 | Valid | 511.3 | 73.3 | 172 ms | 13.6 ms | 8.0 | 0 | 15,339 | 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 | 171.5 | 161.4 | 57 ms | 6.2 ms | 1.0 | 1 | 5,139 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 241.3 | 121.4 | 97 ms | 8.2 ms | 2.0 | 0 | 7,239 | 30.0 s |
| Sustained decode | 32K | 4 | Valid | 383.7 | 96.2 | 153 ms | 10.4 ms | 4.0 | 0 | 11,509 | 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 | 64K | 1 | Valid | 145.3 | 143.1 | 91 ms | 7.0 ms | 1.0 | 1 | 4,357 | 30.0 s |
| Sustained decode | 64K | 2 | Valid | 220.3 | 110.6 | 159 ms | 9.0 ms | 2.0 | 0 | 6,607 | 30.0 s |
| Sustained decode | 64K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 1 | Valid | 116.3 | 116.5 | 147 ms | 8.6 ms | 1.0 | 0 | 3,489 | 30.0 s |
| Sustained decode | 123K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 123K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.