Arao AI
Back to search results

Qwen3.8-9B · Q8_0

Start a discussion
Apple M4 Max128GBOllama v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q8_0) on Apple M4 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

103.18 tok/s

Decode

Decode speed

552.91 tok/s

Prefill

Prefill speed

2.14 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

Today

Last verified

Performance

  1. vLLM · IQ2_XS Decode 251.74 · Prefill 1248.2 ·
  2. Ollama · Q8_0 (current)Decode 103.18 · Prefill 552.91 ·
  3. Strata · IQ2_XS Decode 353.9 · Prefill 1746.97 ·
  4. Strata · IQ3_S Decode 255.89 · Prefill 1167.45 ·

Core figures

Decode (avg)
103.18 tok/s
Prefill (avg)
552.91 tok/s
TTFT (avg)
2.14 s
VRAM (avg)
23.84 GB
MTP acceptance rate
—
TTFB
0.83 GB
Power draw
61.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q8_0
Framework
Ollama
Version
v0.30
Context length
32768 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 M4 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
23.84 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
61.2 W

Sources & evidence

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

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

    v0.30 · macOS 15.0 · CUDA N/A · 32768 ctx

    103.18 tok/s

    Decode

    552.91 tok/s

    Prefill

    2.14 s

    TTFT

    23.84 GB

    VRAM

    —

    MTP

    61.2 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=26 running model_id=52 at Q8_0