Speed test matrix

Fara1.5-27B-AWQ-W4A16 on RTX 3090 24GB

vllm · 0.32.0 · AWQ W4A163 contexts (0–24K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 24K

by @Sandbergllm-inference-bench v0.8.0Measured Oct 29, 2026, 19:53 UTC

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 W4A16
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), 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 Sohailhosseini/Fara1.5-27B-AWQ-W4A16 --max-model-len 32768 --gpu-memory-utilization 0.94 --max-num-seqs 52 --enable-prefix-caching --trust-remote-code --language-model-only --max-cudagraph-capture-size 16

Prefill

prompt tok/s by context length

8K context2,1623,788 ms TTFT

16K context2,0727,831 ms TTFT

24K context1,99812,139 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	47.983 ms TTFT	88.7172 ms TTFT	170.6214 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
16K	45.0352 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
24K	43.9474 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	2,162.0	—	3,788 ms	—	—	1	—	—
Prefill	16K	1	Valid	2,072.0	—	7,831 ms	—	—	1	—	—
Prefill	24K	1	Valid	1,998.0	—	12,139 ms	—	—	1	—	—
Sustained decode	0	1	Valid	47.9	47.9	83 ms	20.9 ms	1.0	0	1,436	30.0 s
Sustained decode	0	2	Valid	88.7	44.4	172 ms	22.5 ms	2.0	0	2,660	30.0 s
Sustained decode	0	4	Valid	170.6	42.7	214 ms	23.4 ms	4.0	0	5,116	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	45.0	45.1	352 ms	22.2 ms	1.0	0	1,350	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	24K	1	Valid	43.9	43.9	474 ms	22.8 ms	1.0	0	1,315	30.0 s
Sustained decode	24K	2	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	24K	4	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	24K	8	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	24K	16	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	24K	32	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	24K	64	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	24K	128	Over capacity	—	—	—	—	—	—	—	—

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