Speed test matrix
INTELLECT-2 on RTX PRO 6000 Blackwell Server Edition 96GB
sglang · 0.5.6.post3.dev9335+gdd15fb57b · FP164 contexts (8K–35K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 35K, 40K
Hardware
- Type
- Discrete GPU
- GPU
- RTX PRO 6000 Blackwell Server Edition
- VRAM
- 96 GB
- OS
- linux
Engine
- Engine
- sglang
- Version
- 0.5.6.post3.dev9335+gdd15fb57b
- Quantization
- FP16
- Backend
- cuda
- Repository
- github.com/sgl-project/sglang
- Build
- cuda-13.2
- Commit
dd15fb57b5ef
Run
- Served model
- intellect
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.6.2
- 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-primeintellect-sglang/bin/sglang" serve --model-path PrimeIntellect/INTELLECT-2 --served-model-name intellect --tp 1 --reasoning-parser deepseek-r1 --tool-call-parser hermes --context-length 40960 --mem-fraction-static 0.78 --enable-metrics --host 0.0.0.0 --port 8000 --api-key <redacted>
Prefill
prompt tok/s by context length8K context5,2761,554 ms TTFT
16K context4,8483,346 ms TTFT
32K context4,2327,634 ms TTFT
35K context4,1488,514 ms TTFT
40K context4,02410,024 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 | 20.963 ms TTFT | 43.196 ms TTFT | 85.4139 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 20.373 ms TTFT | 42.0106 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 19.292 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 35K | 19.096 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 | 5,276.0 | — | 1,554 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 4,848.0 | — | 3,346 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 4,232.0 | — | 7,634 ms | — | — | 1 | — | — |
| Prefill | 35K | 1 | Valid | 4,148.0 | — | 8,514 ms | — | — | 1 | — | — |
| Prefill | 40K | 1 | Valid | 4,024.0 | — | 10,024 ms | — | — | 1 | — | — |
| Sustained decode | 8K | 1 | Valid | 20.9 | 20.9 | 63 ms | 47.9 ms | 1.0 | 0 | 627 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 43.1 | 21.6 | 96 ms | 46.3 ms | 2.0 | 0 | 1,294 | 30.0 s |
| Sustained decode | 8K | 4 | Valid | 85.4 | 21.4 | 139 ms | 46.8 ms | 4.0 | 0 | 2,560 | 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 | 20.3 | 20.3 | 73 ms | 49.2 ms | 1.0 | 0 | 609 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 42.0 | 20.9 | 106 ms | 47.7 ms | 2.0 | 0 | 1,258 | 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 | 19.2 | 19.2 | 92 ms | 52.0 ms | 1.0 | 0 | 576 | 30.0 s |
| Sustained decode | 32K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 35K | 1 | Valid | 19.0 | 19.0 | 96 ms | 52.5 ms | 1.0 | 0 | 571 | 30.0 s |
| Sustained decode | 35K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 35K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 35K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 35K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 35K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 35K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 35K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.