Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · IQ3_S

Start a discussion
Intel Arc A770 16GB16GBStrata v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (IQ3_S) on Intel Arc A770 16GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

110.46 tok/s

Decode

Decode speed

356.07 tok/s

Prefill

Prefill speed

1.37 s

TTFT

Time to first token

7.64 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · IQ3_XS Decode 72.87 · Prefill 292.61 ·
  2. Ollama · Q8_0 Decode 38.64 · Prefill 189.17 ·
  3. Strata · IQ3_S (current)Decode 110.46 · Prefill 356.07 ·

Core figures

Decode (avg)
110.46 tok/s
Prefill (avg)
356.07 tok/s
TTFT (avg)
1.37 s
VRAM (avg)
7.64 GB
MTP acceptance rate
0.77
TTFB
0.88 GB
Power draw
162.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
IQ3_S
Framework
Strata
Version
v0.24
Context length
16384 tokens
Batch size
1024
GPU layers
15
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
Intel Arc A770 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
7.64 GB
OS
Windows 11 23H2
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
162.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.24 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx

    110.46 tok/s

    Decode

    356.07 tok/s

    Prefill

    1.37 s

    TTFT

    7.64 GB

    VRAM

    0.77

    MTP

    162.6 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=97 running model_id=57 at IQ3_S