Arao AI
Back to search results

Qwen3-4B · IQ3_XS

Start a discussion
Apple M1 ProOllama v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (IQ3_XS) on Apple M1 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

98.64 tok/s

Decode

Decode speed

472.33 tok/s

Prefill

Prefill speed

0.26 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

2 days ago

Last verified

Performance

  1. Ollama · IQ3_XS (current)Decode 98.64 · Prefill 472.33 ·
  2. Strata · FP16 Decode 58.73 · Prefill 267.72 ·

Core figures

Decode (avg)
98.64 tok/s
Prefill (avg)
472.33 tok/s
TTFT (avg)
0.26 s
VRAM (avg)
7.31 GB
MTP acceptance rate
—
TTFB
0.79 GB
Power draw
28.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
IQ3_XS
Framework
Ollama
Version
v0.26
Context length
8192 tokens
Batch size
512
GPU layers
28
Flash Attention
Off

Hardware

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

GPU
Apple M1 Pro
Measured VRAM (avg)
7.31 GB
OS
macOS 15.0
Driver
Apple M1 Pro
CUDA
N/A
Power draw
28.7 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

    v0.26 · macOS 15.0 · CUDA N/A · 8192 ctx

    98.64 tok/s

    Decode

    472.33 tok/s

    Prefill

    0.26 s

    TTFT

    7.31 GB

    VRAM

    —

    MTP

    28.7 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=100 running model_id=54 at IQ3_XS