Speed test matrix
Qwen3-8B-AWQ on RTX 3090 24GB
vllm · 0.32.0 · AWQ3 contexts (0–32K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K
Hardware
- Type
- Discrete GPU
- GPU
- RTX 3090
- VRAM
- 24 GB
- CPU
- AMD Ryzen 9 7900X (12C)
- 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), 350 W limit (VBIOS max), PCIe Gen4 x16 | AMD Ryzen 9 7900X 12C | 32 GB DDR5 | Ubuntu 24.04.5, NVIDIA driver 595.99.02 vllm serve Qwen/Qwen3-8B-AWQ --max-model-len 40960 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code
Prefill
prompt tok/s by context length8K context5,7721,430 ms TTFT
16K context5,0143,261 ms TTFT
32K context3,8088,547 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 | 123.125 ms TTFT | 231.618 ms TTFT | 427.027 ms TTFT | 737.338 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity |
| 16K | 92.550 ms TTFT | 148.874 ms TTFT | 243.2115 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 74.288 ms TTFT | 108.8118 ms TTFT | 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 | 5,772.0 | — | 1,430 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 5,014.0 | — | 3,261 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 3,808.0 | — | 8,547 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 123.1 | 124.4 | 25 ms | 8.0 ms | 1.0 | 0 | 3,693 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 231.6 | 117.8 | 18 ms | 8.5 ms | 2.0 | 0 | 6,948 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 427.0 | 109.6 | 27 ms | 9.1 ms | 4.0 | 0 | 12,808 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 737.3 | 96.2 | 38 ms | 10.4 ms | 8.0 | 0 | 22,112 | 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 | 92.5 | 92.7 | 50 ms | 10.8 ms | 1.0 | 0 | 2,775 | 30.0 s |
| Sustained decode | 16K | 2 | Valid | 148.8 | 74.7 | 74 ms | 13.4 ms | 2.0 | 0 | 4,462 | 30.0 s |
| Sustained decode | 16K | 4 | Valid | 243.2 | 61.3 | 115 ms | 16.3 ms | 4.0 | 0 | 7,296 | 30.0 s |
| 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 | 74.2 | 74.4 | 88 ms | 13.4 ms | 1.0 | 0 | 2,227 | 30.0 s |
| Sustained decode | 32K | 2 | Valid | 108.8 | 54.5 | 118 ms | 18.3 ms | 2.0 | 0 | 3,264 | 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 | — | — | — | — | — | — | — | — |
Over capacity: not run because this many requests at this context would exceed the server's KV cache.