Arao AI
Back to search results

Qwen3-4B · Q8_0

Start a discussion
Apple M4 Pro64GBOllama v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (Q8_0) on Apple M4 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

86.82 tok/s

Decode

Decode speed

468.6 tok/s

Prefill

Prefill speed

0.85 s

TTFT

Time to first token

11.76 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · Q5_K_M Decode 115.86 · Prefill 428.93 ·
  2. Ollama · IQ2_XS Decode 164.02 · Prefill 802.68 ·
  3. Ollama · Q8_0 (current)Decode 86.82 · Prefill 468.6 ·

Core figures

Decode (avg)
86.82 tok/s
Prefill (avg)
468.6 tok/s
TTFT (avg)
0.85 s
VRAM (avg)
11.76 GB
MTP acceptance rate
—
TTFB
0.69 GB
Power draw
42.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
Q8_0
Framework
Ollama
Version
v0.53
Context length
16384 tokens
Batch size
256
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 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
11.76 GB
OS
macOS 15.0
Driver
Apple M4 Pro
CUDA
N/A
Power draw
42.3 W

Sources & evidence

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

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

    v0.53 · macOS 15.0 · CUDA N/A · 16384 ctx

    86.82 tok/s

    Decode

    468.6 tok/s

    Prefill

    0.85 s

    TTFT

    11.76 GB

    VRAM

    —

    MTP

    42.3 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=25 running model_id=54 at Q8_0