Speed test matrix
deepseek-r1-distill-qwen-14b-awq on RTX 3090 24GB
vllm · 0.32.0 · AWQ4 contexts (0–48K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 48K
Hardware
- Type
- Discrete GPU
- GPU
- RTX 3090
- VRAM
- 24 GB
- CPU
- Intel Core i7-9700K (8C)
- RAM
- 32 GB
- OS
- Ubuntu 24.04.5
Engine
- Engine
- vllm
- Version
- 0.32.0
- Quantization
- AWQ
- 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 3090 24GB (Zagitta/gpu-unlock), 420 W limit, PCIe Gen3 x16 | Intel Core i7-9700K 8C | 32 GB DDR4 | Ubuntu 24.04.5, NVIDIA driver 580.178.04 vllm serve casperhansen/deepseek-r1-distill-qwen-14b-awq --max-model-len 57344 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code
Prefill
prompt tok/s by context length8K context3,7222,214 ms TTFT
16K context3,2425,038 ms TTFT
32K context2,57712,626 ms TTFT
48K context2,13322,846 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 | 82.237 ms TTFT | 157.338 ms TTFT | 298.036 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 63.2125 ms TTFT | 104.2103 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 51.5191 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 48K | 43.3246 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 | 3,722.0 | — | 2,214 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 3,242.0 | — | 5,038 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 2,577.0 | — | 12,626 ms | — | — | 1 | — | — |
| Prefill | 48K | 1 | Valid | 2,133.0 | — | 22,846 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 82.2 | 82.6 | 37 ms | 12.1 ms | 1.0 | 0 | 2,465 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 157.3 | 79.5 | 38 ms | 12.6 ms | 2.0 | 0 | 4,718 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 298.0 | 75.7 | 36 ms | 13.2 ms | 4.0 | 0 | 8,936 | 30.0 s |
| Sustained decode | 0 | 8 | Over capacity | — | — | — | — | — | — | — | — |
| 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 | 63.2 | 63.3 | 125 ms | 15.8 ms | 1.0 | 0 | 1,894 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 104.2 | 52.2 | 103 ms | 19.1 ms | 2.0 | 0 | 3,125 | 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 | 51.5 | 51.6 | 191 ms | 19.4 ms | 1.0 | 0 | 1,545 | 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 | 48K | 1 | Valid | 43.3 | 43.4 | 246 ms | 23.0 ms | 1.0 | 0 | 1,299 | 30.0 s |
| Sustained decode | 48K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 48K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 48K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 48K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 48K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 48K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 48K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.