Speed test matrix
Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit on RTX 3090 24GB
vllm · 0.32.0 · AWQ 4-bit6 contexts (0–136K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 128K
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 4-bit
- 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: int4_per_token_head # 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 cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit --max-model-len 147456 --gpu-memory-utilization 0.94 --max-num-seqs 128 --enable-prefix-caching --trust-remote-code --kv-cache-dtype int4_per_token_head --attention-backend TRITON_ATTN
Prefill
prompt tok/s by context length8K context4,0782,024 ms TTFT
16K context2,5616,383 ms TTFT
32K context1,47422,077 ms TTFT
64K context792.082,001 ms TTFT
128K context409.0317,551 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 | 126.644 ms TTFT | 220.746 ms TTFT | 382.884 ms TTFT | 616.988 ms TTFT | 985.198 ms TTFT | Over capacity | Over capacity | Over capacity |
| 16K | Looped | Looped | Looped | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 32K | 53.6206 ms TTFT | Looped | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 64K | 33.3414 ms TTFT | 56.0583 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 128K | 18.9Requests queued800 ms TTFT | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity | Over capacity |
| 136K | 17.9Requests queued838 ms TTFT | Over capacity | Over capacity | Over capacity | 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. Looped: the model kept repeating the same text, so the benchmark discarded this measurement. 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 | 4,078.0 | — | 2,024 ms | — | — | 1 | — | — |
| Prefill | 16K | 1 | Valid | 2,561.0 | — | 6,383 ms | — | — | 1 | — | — |
| Prefill | 32K | 1 | Valid | 1,474.0 | — | 22,077 ms | — | — | 1 | — | — |
| Prefill | 64K | 1 | Valid | 792.0 | — | 82,001 ms | — | — | 1 | — | — |
| Prefill | 128K | 1 | Valid | 409.0 | — | 317,551 ms | — | — | 1 | — | — |
| Sustained decode | 0 | 1 | Valid | 126.6 | 128.8 | 44 ms | 7.8 ms | 1.0 | 0 | 3,797 | 30.0 s |
| Sustained decode | 0 | 2 | Valid | 220.7 | 112.5 | 46 ms | 8.9 ms | 2.0 | 0 | 6,622 | 30.0 s |
| Sustained decode | 0 | 4 | Valid | 382.8 | 97.5 | 84 ms | 10.3 ms | 4.0 | 0 | 11,484 | 30.0 s |
| Sustained decode | 0 | 8 | Valid | 616.9 | 79.2 | 88 ms | 12.6 ms | 8.0 | 0 | 18,504 | 30.0 s |
| Sustained decode | 0 | 16 | Valid | 985.1 | 63.7 | 98 ms | 15.7 ms | 16.0 | 0 | 29,552 | 30.0 s |
| Sustained decode | 0 | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 0 | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 16K | 1 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| Sustained decode | 16K | 4 | Looped | — | — | — | — | — | 0 | 0 | — |
| 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 | 53.6 | 53.7 | 206 ms | 18.6 ms | 1.0 | 0 | 1,609 | 30.0 s |
| Sustained decode | 32K | 2 | Looped | — | — | — | — | — | 0 | 0 | — |
| 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 | 64K | 1 | Valid | 33.3 | 33.4 | 414 ms | 30.0 ms | 1.0 | 0 | 999 | 30.0 s |
| Sustained decode | 64K | 2 | Valid | 56.0 | 28.0 | 583 ms | 35.8 ms | 2.0 | 0 | 1,678 | 30.0 s |
| Sustained decode | 64K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 64K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 1 | Requests queued | 18.9 | 19.0 | 800 ms | 52.5 ms | 1.0 | 0 | 566 | 30.0 s |
| Sustained decode | 128K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 128K | 128 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 136K | 1 | Requests queued | 17.9 | 18.1 | 838 ms | 55.4 ms | 1.0 | 0 | 536 | 30.0 s |
| Sustained decode | 136K | 2 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 136K | 4 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 136K | 8 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 136K | 16 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 136K | 32 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 136K | 64 | Over capacity | — | — | — | — | — | — | — | — |
| Sustained decode | 136K | 128 | Over capacity | — | — | — | — | — | — | — | — |
Requests queued: the server could not run all requests at once, so some waited in a queue. Looped: the model kept repeating the same text, so the benchmark discarded this measurement. Over capacity: not run because this many requests at this context would exceed the server's KV cache.