Arao AI
Back to search results

Qwen3-8B · IQ3_XS

Start a discussion
Apple M5 Ultra512GBOllama v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ3_XS) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

108 tok/s

Decode

Decode speed

446.71 tok/s

Prefill

Prefill speed

1.63 s

TTFT

Time to first token

12.52 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_M Decode 102.09 · Prefill 450.54 ·
  2. llama.cpp · Q6_K Decode 73.25 · Prefill 373.92 ·
  3. Ollama · IQ3_XS (current)Decode 108 · Prefill 446.71 ·
  4. Ollama · Q4_K_S Decode 102.76 · Prefill 333.29 ·

Core figures

Decode (avg)
108 tok/s
Prefill (avg)
446.71 tok/s
TTFT (avg)
1.63 s
VRAM (avg)
12.52 GB
MTP acceptance rate
—
TTFB
0.86 GB
Power draw
120.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ3_XS
Framework
Ollama
Version
v0.46
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)
12.52 GB
OS
macOS 26.1
Power draw
120.9 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

    v0.46 · macOS 26.1 · 2048 ctx

    108 tok/s

    Decode

    446.71 tok/s

    Prefill

    1.63 s

    TTFT

    12.52 GB

    VRAM

    —

    MTP

    120.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=53 at IQ3_XS