Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ2_M

Start a discussion
Apple M4 Pro64GBStrata v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ2_M) on Apple M4 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

303.45 tok/s

Decode

Decode speed

1,578.72 tok/s

Prefill

Prefill speed

2.12 s

TTFT

Time to first token

2.65 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Strata · IQ1_S Decode 325.5 · Prefill 1591.11 ·
  2. Strata · IQ2_M (current)Decode 303.45 · Prefill 1578.72 ·

Core figures

Decode (avg)
303.45 tok/s
Prefill (avg)
1,578.72 tok/s
TTFT (avg)
2.12 s
VRAM (avg)
2.65 GB
MTP acceptance rate
0.72
TTFB
2.43 GB
Power draw
47.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ2_M
Framework
Strata
Version
v0.24
Context length
16384 tokens
Batch size
512
GPU layers
15
Flash Attention
On

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)
2.65 GB
OS
macOS 15.0
Driver
Apple M4 Pro
CUDA
N/A
Power draw
47.6 W

Sources & evidence

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

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

    v0.24 · macOS 15.0 · CUDA N/A · 16384 ctx

    303.45 tok/s

    Decode

    1,578.72 tok/s

    Prefill

    2.12 s

    TTFT

    2.65 GB

    VRAM

    0.72

    MTP

    47.6 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=25 running model_id=59 at IQ2_M