Arao AI
Back to search results

Qwen3-1.7B · IQ2_XS

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBOllama v0.50L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (IQ2_XS) on NVIDIA RTX 4060 Ti 16GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

184.49 tok/s

Decode

Decode speed

897.89 tok/s

Prefill

Prefill speed

2.43 s

TTFT

Time to first token

3.81 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · IQ1_S Decode 203.18 · Prefill 859.41 ·
  2. Ollama · IQ2_XS (current)Decode 184.49 · Prefill 897.89 ·

Core figures

Decode (avg)
184.49 tok/s
Prefill (avg)
897.89 tok/s
TTFT (avg)
2.43 s
VRAM (avg)
3.81 GB
MTP acceptance rate
—
TTFB
1.48 GB
Power draw
352.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
IQ2_XS
Framework
Ollama
Version
v0.50
Context length
4096 tokens
Batch size
512
GPU layers
33
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)
3.81 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.8
Power draw
352.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.50 · Ubuntu 22.04 · CUDA 12.8 · 4096 ctx

    184.49 tok/s

    Decode

    897.89 tok/s

    Prefill

    2.43 s

    TTFT

    3.81 GB

    VRAM

    —

    MTP

    352.8 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=3 running model_id=55 at IQ2_XS