Arao AI
Back to search results

Qwen3-8B · IQ3_XS

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBllama.cpp v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ3_XS) on NVIDIA RTX 4060 Ti 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

120.55 tok/s

Decode

Decode speed

447.58 tok/s

Prefill

Prefill speed

0.15 s

TTFT

Time to first token

12.52 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_XS (current)Decode 120.55 · Prefill 447.58 ·
  2. llama.cpp · Q2_K Decode 129.58 · Prefill 532.02 ·
  3. vLLM · Q3_K_L Decode 108.14 · Prefill 543.11 ·
  4. vLLM · IQ3_XS Decode 103.03 · Prefill 480.63 ·

Core figures

Decode (avg)
120.55 tok/s
Prefill (avg)
447.58 tok/s
TTFT (avg)
0.15 s
VRAM (avg)
12.52 GB
MTP acceptance rate
—
TTFB
0.96 GB
Power draw
151.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ3_XS
Framework
llama.cpp
Version
v0.27
Context length
4096 tokens
Batch size
256
GPU layers
99
Flash Attention
Off

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)
12.52 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.8
Power draw
151.4 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

    v0.27 · Ubuntu 22.04 · CUDA 12.8 · 4096 ctx

    120.55 tok/s

    Decode

    447.58 tok/s

    Prefill

    0.15 s

    TTFT

    12.52 GB

    VRAM

    —

    MTP

    151.4 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=3 running model_id=53 at IQ3_XS