Arao AI
Back to search results

Qwen3.5-27B · IQ3_XS

Start a discussion
Apple M5 Max128GBOllama v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (IQ3_XS) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

62.24 tok/s

Decode

Decode speed

282.1 tok/s

Prefill

Prefill speed

0.81 s

TTFT

Time to first token

37.25 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 · Q2_K Decode 65.62 · Prefill 279.34 ·
  2. Ollama · IQ2_M Decode 64.33 · Prefill 209.5 ·
  3. Ollama · IQ3_XS (current)Decode 62.24 · Prefill 282.1 ·
  4. llama.cpp · IQ3_XS Decode 171.72 · Prefill 594.08 ·
  5. llama.cpp · Q4_K_S Decode 146.98 · Prefill 610.13 ·
  6. Ollama · Q5_K_M Decode 119.42 · Prefill 542.35 ·
  7. Ollama · Q6_K Decode 100.18 · Prefill 374.17 ·

Core figures

Decode (avg)
62.24 tok/s
Prefill (avg)
282.1 tok/s
TTFT (avg)
0.81 s
VRAM (avg)
37.25 GB
MTP acceptance rate
—
TTFB
0.5 GB
Power draw
52.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
IQ3_XS
Framework
Ollama
Version
v0.48
Context length
8192 tokens
Batch size
256
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 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
37.25 GB
OS
macOS 26.1
Power draw
52.9 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

    v0.48 · macOS 26.1 · 8192 ctx

    62.24 tok/s

    Decode

    282.1 tok/s

    Prefill

    0.81 s

    TTFT

    37.25 GB

    VRAM

    —

    MTP

    52.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=28 running model_id=50 at IQ3_XS