Arao AI
Back to search results

Qwen3-4B · IQ2_XS

Start a discussion
Apple M4 Pro64GBOllama v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (IQ2_XS) on Apple M4 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

164.02 tok/s

Decode

Decode speed

802.68 tok/s

Prefill

Prefill speed

1.28 s

TTFT

Time to first token

6.13 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 · Q5_K_M Decode 115.86 · Prefill 428.93 ·
  2. Ollama · IQ2_XS (current)Decode 164.02 · Prefill 802.68 ·
  3. Ollama · Q8_0 Decode 86.82 · Prefill 468.6 ·

Core figures

Decode (avg)
164.02 tok/s
Prefill (avg)
802.68 tok/s
TTFT (avg)
1.28 s
VRAM (avg)
6.13 GB
MTP acceptance rate
—
TTFB
1.31 GB
Power draw
96 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
IQ2_XS
Framework
Ollama
Version
v0.29
Context length
4096 tokens
Batch size
256
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 M4 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
6.13 GB
OS
macOS 15.0
Driver
Apple M4 Pro
CUDA
N/A
Power draw
96 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

    v0.29 · macOS 15.0 · CUDA N/A · 4096 ctx

    164.02 tok/s

    Decode

    802.68 tok/s

    Prefill

    1.28 s

    TTFT

    6.13 GB

    VRAM

    —

    MTP

    96 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=25 running model_id=54 at IQ2_XS