Speed test matrix

Qwen3-0.6B-FP8 on RTX 3060 12GB

vllm · 0.32.0 · FP83 contexts (0–32K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K

by @Sandbergllm-inference-bench v0.8.0Measured Oct 31, 2026, 00:43 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: FP8
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-FP8 --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 context9,704846 ms TTFT

16K context7,0832,294 ms TTFT

32K context4,4257,310 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	185.045 ms TTFT	298.272 ms TTFT	459.759 ms TTFT	665.499 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity
16K	90.5150 ms TTFT	113.5204 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
32K	57.1252 ms TTFT	66.2367 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	9,704.0	—	846 ms	—	—	1	—	—
Prefill	16K	1	Valid	7,083.0	—	2,294 ms	—	—	1	—	—
Prefill	32K	1	Valid	4,425.0	—	7,310 ms	—	—	1	—	—
Sustained decode	0	1	Valid	185.0	196.6	45 ms	5.1 ms	1.0	0	5,548	30.0 s
Sustained decode	0	2	Valid	298.2	162.2	72 ms	6.2 ms	2.0	0	8,943	30.0 s
Sustained decode	0	4	Valid	459.7	129.2	59 ms	7.7 ms	4.0	0	13,792	30.0 s
Sustained decode	0	8	Valid	665.4	98.0	99 ms	10.2 ms	8.0	0	19,960	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	90.5	91.2	150 ms	11.0 ms	1.0	0	2,715	30.0 s
Sustained decode	16K	2	Valid	113.5	57.0	204 ms	17.5 ms	2.0	0	3,404	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	57.1	57.3	252 ms	17.5 ms	1.0	0	1,711	30.0 s
Sustained decode	32K	2	Valid	66.2	33.2	367 ms	30.1 ms	2.0	0	1,986	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.