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. KV cache: fp8 # 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 --kv-cache-dtype fp8
Prefill
prompt tok/s by context length8K context1,5945,112 ms TTFT
16K context1,50210,735 ms TTFT
32K context1,38223,229 ms TTFT
56K context1,22945,620 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 | 53.7104 ms TTFT | 104.8174 ms TTFT | 200.5275 ms TTFT | 367.0498 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 51.5338 ms TTFT | 98.1469 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 49.5562 ms TTFT | 91.9772 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 56K | 46.8405 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 | 1,594.0 | — | 5,112 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 1,502.0 | — | 10,735 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 1,382.0 | — | 23,229 ms | — | — | 1 | — | — |
| Prefill | 56K | 1 | Valid | 1,229.0 | — | 45,620 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 53.7 | 53.8 | 104 ms | 18.6 ms | 1.0 | 0 | 1,611 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 104.8 | 52.5 | 174 ms | 19.0 ms | 2.0 | 0 | 3,145 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 200.5 | 50.2 | 275 ms | 19.9 ms | 4.0 | 0 | 6,015 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 367.0 | 46.1 | 498 ms | 21.7 ms | 8.0 | 0 | 11,011 | 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 | 51.5 | 51.6 | 338 ms | 19.4 ms | 1.0 | 0 | 1,546 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 98.1 | 48.9 | 469 ms | 20.4 ms | 2.0 | 0 | 2,942 | 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 | 49.5 | 49.6 | 562 ms | 20.1 ms | 1.0 | 0 | 1,486 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 91.9 | 45.8 | 772 ms | 21.8 ms | 2.0 | 0 | 2,756 | 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 | 46.9 | 405 ms | 21.3 ms | 1.0 | 0 | 1,405 | 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.