Arao AI
Back to search results

Llama-3.2-3B-Instruct · Q5_K_M

Start a discussion
NVIDIA RTX 3060 12GB12GBvLLM v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.2-3B-Instruct (Q5_K_M) on NVIDIA RTX 3060 12GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

143.38 tok/s

Decode

Decode speed

521.02 tok/s

Prefill

Prefill speed

1.74 s

TTFT

Time to first token

7.96 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 Decode 126.84 · Prefill 630.8 ·
  3. vLLM · Q5_K_M (current)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)
143.38 tok/s
Prefill (avg)
521.02 tok/s
TTFT (avg)
1.74 s
VRAM (avg)
7.96 GB
MTP acceptance rate
—
TTFB
1.15 GB
Power draw
157.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.2-3B-Instruct
Quantization
Q5_K_M
Framework
vLLM
Version
v0.34
Context length
32768 tokens
Batch size
8
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 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
7.96 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.8
Power draw
157.1 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

    v0.34 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    143.38 tok/s

    Decode

    521.02 tok/s

    Prefill

    1.74 s

    TTFT

    7.96 GB

    VRAM

    —

    MTP

    157.1 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=15 running model_id=70 at Q5_K_M