Speed test matrix

NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit on RTX 3060 12GB

vllm · 0.32.0 · AWQ 4-bit3 contexts (0–32K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K

by @Sandbergllm-inference-bench v0.8.0Measured Oct 31, 2026, 17:05 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: 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: fp8
# 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 cyankiwi/NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit --max-model-len 40960 --gpu-memory-utilization 0.94 --max-num-seqs 34 --enable-prefix-caching --trust-remote-code --kv-cache-dtype fp8 --max-cudagraph-capture-size 16

Prefill

prompt tok/s by context length

8K context1,0348,071 ms TTFT

16K context999.016,524 ms TTFT

32K context956.034,394 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	40.8134 ms TTFT	78.1692 ms TTFT	144.6397 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
16K	39.81,009 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
32K	38.81,955 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	1,034.0	—	8,071 ms	—	—	1	—	—
Prefill	16K	1	Valid	999.0	—	16,524 ms	—	—	1	—	—
Prefill	32K	1	Valid	956.0	—	34,394 ms	—	—	1	—	—
Sustained decode	0	1	Valid	40.8	40.8	134 ms	24.5 ms	1.0	0	1,222	30.0 s
Sustained decode	0	2	Valid	78.1	39.1	692 ms	25.6 ms	2.0	0	2,342	30.0 s
Sustained decode	0	4	Valid	144.6	36.2	397 ms	27.6 ms	4.0	0	4,335	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	39.8	39.8	1,009 ms	25.1 ms	1.0	0	1,192	30.0 s
Sustained decode	16K	2	Over capacity	—	—	—	—	—	—	—	—
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	38.8	38.9	1,955 ms	25.7 ms	1.0	0	1,164	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	—	—	—	—	—	—	—	—

Over capacity: not run because this many requests at this context would exceed the server's KV cache.