Speed test matrix
gemma-4-31B-it on H200 NVL 141GB
sglang · 0.5.6.post3.dev5791+gf7d4e44d8 · BF168 contexts (8K–1024K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K
Hardware
- Type
- Discrete GPU
- GPU
- H200 NVL
- VRAM
- 141 GB
- OS
- linux
Engine
- Engine
- sglang
- Version
- 0.5.6.post3.dev5791+gf7d4e44d8
- Quantization
- BF16
- Backend
- cuda
- Repository
- github.com/sgl-project/sglang
- Build
- cuda-13.2
- Commit
f7d4e44d82ac
Run
- Served model
- gemma
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.4.29
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 8,192 tokens
Launch command
"$HOME/env_h200-gemma-sglang/bin/sglang" serve --model-path google/gemma-4-31B-it --served-model-name gemma --trust-remote-code --tp 1 --reasoning-parser gemma4 --tool-call-parser gemma4 --context-length 262144 --mem-fraction-static 0.848736 --enable-metrics --host 0.0.0.0 --port 8000 --api-key <redacted>
Prefill
prompt tok/s by context length8K context4,7651,721 ms TTFT
16K context3,7584,327 ms TTFT
32K context2,70511,965 ms TTFT
64K context1,74137,091 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 | 44.2Requests queued115 ms TTFT | 87.8153 ms TTFT | 175.0209 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 40.9157 ms TTFT | 81.9212 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 35.9228 ms TTFT | 72.5306 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 28.6389 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 128K | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 256K | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 512K | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 1024K | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
Requests queued: the server could not run all requests at once, so some waited in a queue. 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 | 4,765.0 | — | 1,721 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 3,758.0 | — | 4,327 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 2,705.0 | — | 11,965 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 1,741.0 | — | 37,091 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Requests queued | 44.2 | 44.2 | 115 ms | 22.6 ms | 1.0 | 0 | 1,324 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 87.8 | 43.9 | 153 ms | 22.8 ms | 2.0 | 0 | 2,632 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 175.0 | 43.8 | 209 ms | 22.9 ms | 4.0 | 0 | 5,246 | 30.0 s |
| Sustained decode | 8K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 40.9 | 40.9 | 157 ms | 24.5 ms | 1.0 | 0 | 1,226 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 81.9 | 40.9 | 212 ms | 24.4 ms | 2.0 | 0 | 2,456 | 30.0 s |
| Sustained decode | 16K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 35.9 | 35.9 | 228 ms | 27.8 ms | 1.0 | 0 | 1,076 | 29.9 s |
| Sustained decode | 32K | 2 | Valid | 72.5 | 36.2 | 306 ms | 27.6 ms | 2.0 | 0 | 2,173 | 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 | 64K | 1 | Valid | 28.6 | 28.5 | 389 ms | 35.0 ms | 1.0 | 0 | 856 | 30.0 s |
| Sustained decode | 64K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 128K | 1 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 256K | 1 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 256K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 256K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 256K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 256K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 256K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 256K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 256K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 512K | 1 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 512K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 512K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 512K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 512K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 512K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 512K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 512K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 1024K | 1 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 1024K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 1024K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 1024K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 1024K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 1024K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 1024K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 1024K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Requests queued: the server could not run all requests at once, so some waited in a queue. Over capacity: not run because this many requests at this context would exceed the server's KV cache.
