Arao AI
Back to search results

Qwen3.5-27B · IQ2_M

Start a discussion
Apple M2 UltraOllama v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (IQ2_M) on Apple M2 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

104.98 tok/s

Decode

Decode speed

551.16 tok/s

Prefill

Prefill speed

2 s

TTFT

Time to first token

31.58 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 · Q3_K_L Decode 82.49 · Prefill 401.83 ·
  2. Ollama · IQ2_M (current)Decode 104.98 · Prefill 551.16 ·
  3. Ollama · Q8_0 Decode 49.84 · Prefill 240.92 ·
  4. Strata · Q4_K_M Decode 113.85 · Prefill 614.05 ·

Core figures

Decode (avg)
104.98 tok/s
Prefill (avg)
551.16 tok/s
TTFT (avg)
2 s
VRAM (avg)
31.58 GB
MTP acceptance rate
—
TTFB
0.84 GB
Power draw
101.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
IQ2_M
Framework
Ollama
Version
v0.28
Context length
16384 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 M2 Ultra
Measured VRAM (avg)
31.58 GB
OS
macOS 26.1
Power draw
101.9 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

    v0.28 · macOS 26.1 · 16384 ctx

    104.98 tok/s

    Decode

    551.16 tok/s

    Prefill

    2 s

    TTFT

    31.58 GB

    VRAM

    —

    MTP

    101.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=103 running model_id=50 at IQ2_M