Arao AI
Back to search results

Qwen3.5-0.8B · Q8_0

Start a discussion
Apple M5 Ultra512GBllama.cpp v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q8_0) on Apple M5 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

165.05 tok/s

Decode

Decode speed

859.2 tok/s

Prefill

Prefill speed

0.78 s

TTFT

Time to first token

4.03 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 · Q8_0 (current)Decode 165.05 · Prefill 859.2 ·
  2. Ollama · IQ2_M Decode 328.08 · Prefill 1800.71 ·
  3. Ollama · IQ3_XS Decode 260.88 · Prefill 1003.67 ·

Core figures

Decode (avg)
165.05 tok/s
Prefill (avg)
859.2 tok/s
TTFT (avg)
0.78 s
VRAM (avg)
4.03 GB
MTP acceptance rate
—
TTFB
1.32 GB
Power draw
115.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q8_0
Framework
llama.cpp
Version
v0.30
Context length
4096 tokens
Batch size
512
GPU layers
20
Flash Attention
On

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)
4.03 GB
OS
macOS 26.1
Power draw
115.5 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

    v0.30 · macOS 26.1 · 4096 ctx

    165.05 tok/s

    Decode

    859.2 tok/s

    Prefill

    0.78 s

    TTFT

    4.03 GB

    VRAM

    —

    MTP

    115.5 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=29 running model_id=51 at Q8_0