Arao AI
Back to search results

Qwen3.8-9B · Q8_0

Start a discussion
Apple M5 Ultra512GBOllama v0.55L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q8_0) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

57.41 tok/s

Decode

Decode speed

209.64 tok/s

Prefill

Prefill speed

0.86 s

TTFT

Time to first token

23.84 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 130.42 · Prefill 681.87 ·
  2. Ollama · Q8_0 (current)Decode 57.41 · Prefill 209.64 ·

Core figures

Decode (avg)
57.41 tok/s
Prefill (avg)
209.64 tok/s
TTFT (avg)
0.86 s
VRAM (avg)
23.84 GB
MTP acceptance rate
—
TTFB
0.46 GB
Power draw
134.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q8_0
Framework
Ollama
Version
v0.55
Context length
2048 tokens
Batch size
512
GPU layers
20
Flash Attention
Off

Hardware

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

GPU
Apple M5 Ultra
Nominal VRAM
512 GB
Measured VRAM (avg)
23.84 GB
OS
macOS 26.1
Power draw
134.8 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.55 · macOS 26.1 · 2048 ctx

    57.41 tok/s

    Decode

    209.64 tok/s

    Prefill

    0.86 s

    TTFT

    23.84 GB

    VRAM

    —

    MTP

    134.8 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=52 at Q8_0