Arao AI
Back to search results

Qwen3-8B · IQ1_S

Start a discussion
Apple M5 Pro64GBOllama v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ1_S) on Apple M5 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

187.29 tok/s

Decode

Decode speed

770.8 tok/s

Prefill

Prefill speed

0.44 s

TTFT

Time to first token

9.16 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · IQ1_S (current)Decode 187.29 · Prefill 770.8 ·
  2. Ollama · Q4_K_S Decode 116.66 · Prefill 579.89 ·
  3. Strata · Q3_K_L Decode 212.69 · Prefill 1110.56 ·

Core figures

Decode (avg)
187.29 tok/s
Prefill (avg)
770.8 tok/s
TTFT (avg)
0.44 s
VRAM (avg)
9.16 GB
MTP acceptance rate
—
TTFB
1.5 GB
Power draw
141.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ1_S
Framework
Ollama
Version
v0.31
Context length
4096 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

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

GPU
Apple M5 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
9.16 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
141.6 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

    v0.31 · macOS 15.0 · CUDA N/A · 4096 ctx

    187.29 tok/s

    Decode

    770.8 tok/s

    Prefill

    0.44 s

    TTFT

    9.16 GB

    VRAM

    —

    MTP

    141.6 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=27 running model_id=53 at IQ1_S