Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · Q8_0

Start a discussion
Apple M2 ProOllama v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q8_0) on Apple M2 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

140.52 tok/s

Decode

Decode speed

749.46 tok/s

Prefill

Prefill speed

1.4 s

TTFT

Time to first token

3.31 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · Q3_K_L Decode 248.22 · Prefill 810.72 ·
  2. Ollama · Q5_K_S Decode 165.81 · Prefill 551.58 ·
  3. Ollama · Q8_0 (current)Decode 140.52 · Prefill 749.46 ·

Core figures

Decode (avg)
140.52 tok/s
Prefill (avg)
749.46 tok/s
TTFT (avg)
1.4 s
VRAM (avg)
3.31 GB
MTP acceptance rate
—
TTFB
1.12 GB
Power draw
68.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
Q8_0
Framework
Ollama
Version
v0.23
Context length
4096 tokens
Batch size
512
GPU layers
33
Flash Attention
On

Hardware

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

GPU
Apple M2 Pro
Measured VRAM (avg)
3.31 GB
OS
macOS 15.0
Driver
Apple M2 Pro
CUDA
N/A
Power draw
68.3 W

Sources & evidence

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

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

    v0.23 · macOS 15.0 · CUDA N/A · 4096 ctx

    140.52 tok/s

    Decode

    749.46 tok/s

    Prefill

    1.4 s

    TTFT

    3.31 GB

    VRAM

    —

    MTP

    68.3 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=102 running model_id=59 at Q8_0