Speed test matrix

Qwen3-0.6B on RTX 3060 12GB

vllm · 0.32.0 · BF163 contexts (0–32K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K

by @Sandbergllm-inference-bench v0.8.0Measured Oct 31, 2026, 15:09 UTC

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
# 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/Qwen3-0.6B --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 length

8K context1,1117,388 ms TTFT

16K context7,1052,287 ms TTFT

32K context4,4027,348 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	155.840 ms TTFT	256.469 ms TTFT	415.683 ms TTFT	625.6101 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity
16K	80.9146 ms TTFT	103.8202 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
32K	52.9250 ms TTFT	62.5357 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	1,111.0	—	7,388 ms	—	—	1	—	—
Prefill	16K	1	Valid	7,105.0	—	2,287 ms	—	—	1	—	—
Prefill	32K	1	Valid	4,402.0	—	7,348 ms	—	—	1	—	—
Sustained decode	0	1	Valid	155.8	162.2	40 ms	6.2 ms	1.0	0	4,674	30.0 s
Sustained decode	0	2	Valid	256.4	135.3	69 ms	7.4 ms	2.0	0	7,690	30.0 s
Sustained decode	0	4	Valid	415.6	112.6	83 ms	8.9 ms	4.0	0	12,468	30.0 s
Sustained decode	0	8	Valid	625.6	88.4	101 ms	11.3 ms	8.0	0	18,768	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	80.9	81.4	146 ms	12.3 ms	1.0	0	2,426	30.0 s
Sustained decode	16K	2	Valid	103.8	52.1	202 ms	19.2 ms	2.0	0	3,113	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	52.9	53.1	250 ms	18.8 ms	1.0	0	1,588	30.0 s
Sustained decode	32K	2	Valid	62.5	31.3	357 ms	31.9 ms	2.0	0	1,874	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.