Speed test matrix
Qwen3-1.7B on RTX 3060 12GB
vllm · 0.32.0 · BF162 contexts (0–8K) × 8 concurrency levels (1–128) · prefill at 8K, 64K
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
- BF16
- 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 Qwen/Qwen3-1.7B --max-model-len 16384 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code --kv-cache-dtype fp8
Prefill
prompt tok/s by context length8K context2,7882,941 ms TTFT
64K context1,08859,171 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 | 76.455 ms TTFT | 148.741 ms TTFT | 286.719,022 ms TTFT | 522.769 ms TTFT | 979.3Requests queued58,889 ms TTFT | Over capacity | Over capacity | Over capacity |
| 8K | 69.96,851 ms TTFT | 132.7170 ms TTFT | Over capacity | 356.0325 ms TTFT | 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 | 2,788.0 | — | 2,941 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 1,088.0 | — | 59,171 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 76.4 | 76.7 | 55 ms | 13.0 ms | 1.0 | 0 | 2,292 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 148.7 | 74.8 | 41 ms | 13.4 ms | 2.0 | 0 | 4,460 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 286.7 | 72.3 | 19,022 ms | 13.8 ms | 4.0 | 0 | 8,600 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 522.7 | 66.7 | 69 ms | 15.0 ms | 8.0 | 0 | 15,680 | 30.0 s |
| Sustained decode | 0 | 16 | Requests queued | 979.3 | 61.9 | 58,889 ms | 16.2 ms | 16.0 | 0 | 29,376 | 30.0 s |
| Sustained decode | 0 | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 1 | Valid | 69.9 | 70.1 | 6,851 ms | 14.3 ms | 1.0 | 0 | 2,096 | 30.0 s |
| Sustained decode | 8K | 2 | Valid | 132.7 | 66.6 | 170 ms | 15.0 ms | 2.0 | 0 | 3,982 | 30.0 s |
| Sustained decode | 8K | 4 | Over capacity | — | — | — | — | 1.0 | 0 | 0 | 30.0 s |
| Sustained decode | 8K | 8 | Valid | 356.0 | 44.8 | 325 ms | 22.3 ms | 8.0 | 0 | 10,672 | 30.0 s |
| Sustained decode | 8K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 8K | 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.