Speed test matrix
Ornith-1.5-9B-NVFP4 on RTX 3060 12GB
vllm · 0.32.0 · NVFP44 contexts (0–56K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 56K
Hardware
- Type
- Discrete GPU
- GPU
- RTX 3060
- VRAM
- 12 GB
- CPU
- Intel Xeon E5-2680 v4 (14C)
- RAM
- 32 GB
- OS
- Ubuntu 24.04.5
Engine
- Engine
- vllm
- Version
- 0.32.0
- Quantization
- NVFP4
- Backend
- cuda
- Repository
- github.com/vllm-project/vllm
- Build
- vllm/vllm-openai:v0.32.0-x86_64
Run
- Served model
- bench
- Revision
- main
- Benchmark tool
- llm-inference-bench v0.8.0
- Decode test
- Fixed duration
- Prefill mode
- Measured during decode warm-up
- Time per measurement
- 30 s
- Max output
- 8,192 tokens
Launch command
# Untuned out-of-the-box baseline. Spec decode: none # 1x RTX 3060 12GB, stock 170 W limit, PCIe Gen3 x16 | Intel Xeon E5-2680 v4 14C | 32 GB DDR4-2400 | Ubuntu 24.04.5, NVIDIA driver 580.178.04 vllm serve ornith-ai/Ornith-1.5-9B-NVFP4 --max-model-len 65536 --gpu-memory-utilization 0.94 --max-num-seqs 73 --enable-prefix-caching --trust-remote-code --language-model-only
Prefill
prompt tok/s by context length8K context1,5995,099 ms TTFT
16K context1,50510,712 ms TTFT
32K context1,38523,181 ms TTFT
56K context1,22845,640 ms TTFT
Sustained decode
total tok/s · rows are context length, columns are simultaneous requests| Context | 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128 |
|---|---|---|---|---|---|---|---|---|
| 0 | 53.7105 ms TTFT | 104.9154 ms TTFT | 200.6282 ms TTFT | 367.1493 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 51.6340 ms TTFT | 98.0484 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 49.6571 ms TTFT | 91.8767 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 56K | 46.8383 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 | 1,599.0 | — | 5,099 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 1,505.0 | — | 10,712 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 1,385.0 | — | 23,181 ms | — | — | 1 | — | — |
| Prefill | 56K | 1 | Valid | 1,228.0 | — | 45,640 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 53.7 | 53.8 | 105 ms | 18.6 ms | 1.0 | 0 | 1,611 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 104.9 | 52.5 | 154 ms | 19.0 ms | 2.0 | 0 | 3,146 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 200.6 | 50.2 | 282 ms | 19.9 ms | 4.0 | 0 | 6,016 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 367.1 | 46.1 | 493 ms | 21.7 ms | 8.0 | 0 | 11,008 | 30.0 s |
| Sustained decode | 0 | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Valid | 51.6 | 51.6 | 340 ms | 19.4 ms | 1.0 | 0 | 1,546 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 98.0 | 48.9 | 484 ms | 20.4 ms | 2.0 | 0 | 2,938 | 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 | 49.6 | 49.7 | 571 ms | 20.1 ms | 1.0 | 0 | 1,487 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 91.8 | 45.8 | 767 ms | 21.9 ms | 2.0 | 0 | 2,752 | 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 | 56K | 1 | Valid | 46.8 | 47.0 | 383 ms | 21.3 ms | 1.0 | 0 | 1,404 | 30.0 s |
| Sustained decode | 56K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 56K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.