Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · IQ3_XS

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBStrata v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (IQ3_XS) on NVIDIA RTX 4060 Ti 16GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

160.63 tok/s

Decode

Decode speed

538.1 tok/s

Prefill

Prefill speed

1.55 s

TTFT

Time to first token

7.31 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · IQ3_S Decode 108.19 · Prefill 350.2 ·
  2. vLLM · Q3_K_M Decode 119.54 · Prefill 394.34 ·
  3. Strata · IQ3_XS (current)Decode 160.63 · Prefill 538.1 ·
  4. Strata · Q3_K_L Decode 140.78 · Prefill 483.92 ·

Core figures

Decode (avg)
160.63 tok/s
Prefill (avg)
538.1 tok/s
TTFT (avg)
1.55 s
VRAM (avg)
7.31 GB
MTP acceptance rate
0.47
TTFB
1.29 GB
Power draw
374.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
IQ3_XS
Framework
Strata
Version
v0.43
Context length
2048 tokens
Batch size
512
GPU layers
12
Flash Attention
On

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)
7.31 GB
OS
macOS 15.0
Driver
570.86
CUDA
12.6
Power draw
374.3 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

    v0.43 · macOS 15.0 · CUDA 12.6 · 2048 ctx

    160.63 tok/s

    Decode

    538.1 tok/s

    Prefill

    1.55 s

    TTFT

    7.31 GB

    VRAM

    0.47

    MTP

    374.3 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=3 running model_id=57 at IQ3_XS