Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q5_K_S

Start a discussion
NVIDIA RTX 3060 12GB12GBllama.cpp v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q5_K_S) on NVIDIA RTX 3060 12GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

126.84 tok/s

Decode

Decode speed

630.8 tok/s

Prefill

Prefill speed

0.66 s

TTFT

Time to first token

7.77 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 193.44 · Prefill 733.2 ·
  2. llama.cpp · Q5_K_S (current)Decode 126.84 · Prefill 630.8 ·
  3. vLLM · Q5_K_M Decode 143.38 · Prefill 521.02 ·
  4. llama.cpp · Q8_0 Decode 87.8 · Prefill 658.5 ·
  5. llama.cpp · Q5_K_M Decode 127.6 · Prefill 957 ·
  6. llama.cpp · Q4_K_M Decode 156 · Prefill 1170 ·

Core figures

Decode (avg)
126.84 tok/s
Prefill (avg)
630.8 tok/s
TTFT (avg)
0.66 s
VRAM (avg)
7.77 GB
MTP acceptance rate
—
TTFB
1.01 GB
Power draw
150.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q5_K_S
Framework
llama.cpp
Version
v0.25
Context length
16384 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
7.77 GB
OS
Windows 11 24H2
Driver
565.57
CUDA
12.4
Power draw
150.4 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

    v0.25 · Windows 11 24H2 · CUDA 12.4 · 16384 ctx

    126.84 tok/s

    Decode

    630.8 tok/s

    Prefill

    0.66 s

    TTFT

    7.77 GB

    VRAM

    —

    MTP

    150.4 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=15 running model_id=70 at Q5_K_S