Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q2_K

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBvLLM v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q2_K) on NVIDIA RTX 4060 Ti 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

350.23 tok/s

Decode

Decode speed

1,317.38 tok/s

Prefill

Prefill speed

0.97 s

TTFT

Time to first token

5.57 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ3_S Decode 326.89 · Prefill 1104.91 ·
  2. vLLM · Q2_K (current)Decode 350.23 · Prefill 1317.38 ·

Core figures

Decode (avg)
350.23 tok/s
Prefill (avg)
1,317.38 tok/s
TTFT (avg)
0.97 s
VRAM (avg)
5.57 GB
MTP acceptance rate
—
TTFB
2.8 GB
Power draw
151.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q2_K
Framework
vLLM
Version
v0.31
Context length
2048 tokens
Batch size
16
GPU layers
999
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 4060 Ti 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
5.57 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.6
Power draw
151.1 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.31 · Ubuntu 22.04 · CUDA 12.6 · 2048 ctx

    350.23 tok/s

    Decode

    1,317.38 tok/s

    Prefill

    0.97 s

    TTFT

    5.57 GB

    VRAM

    —

    MTP

    151.1 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=3 running model_id=70 at Q2_K