Arao AI
Back to search results

Qwen3-8B · IQ3_S

Start a discussion
NVIDIA RTX 3060 12GB12GBvLLM v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ3_S) on NVIDIA RTX 3060 12GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

64 tok/s

Decode

Decode speed

232.21 tok/s

Prefill

Prefill speed

0.64 s

TTFT

Time to first token

11.4 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 70.85 · Prefill 298.67 ·
  2. vLLM · IQ3_S (current)Decode 64 · Prefill 232.21 ·
  3. llama.cpp · IQ3_S Decode 81.43 · Prefill 366.11 ·

Core figures

Decode (avg)
64 tok/s
Prefill (avg)
232.21 tok/s
TTFT (avg)
0.64 s
VRAM (avg)
11.4 GB
MTP acceptance rate
—
TTFB
0.51 GB
Power draw
161.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ3_S
Framework
vLLM
Version
v0.53
Context length
8192 tokens
Batch size
32
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)
11.4 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.4
Power draw
161.6 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

    v0.53 · Windows 11 23H2 · CUDA 12.4 · 8192 ctx

    64 tok/s

    Decode

    232.21 tok/s

    Prefill

    0.64 s

    TTFT

    11.4 GB

    VRAM

    —

    MTP

    161.6 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=15 running model_id=53 at IQ3_S