Arao AI
Back to search results

Qwen3.5-27B · Q5_K_S

Start a discussion
Apple M4 Max128GBOllama v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (Q5_K_S) on Apple M4 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

111.59 tok/s

Decode

Decode speed

447.41 tok/s

Prefill

Prefill speed

0.67 s

TTFT

Time to first token

53.13 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ3_S Decode 165.6 · Prefill 722.22 ·
  2. vLLM · Q3_K_M Decode 166.04 · Prefill 735.49 ·
  3. Ollama · Q3_K_S Decode 165.47 · Prefill 649.98 ·
  4. Ollama · Q5_K_S (current)Decode 111.59 · Prefill 447.41 ·

Core figures

Decode (avg)
111.59 tok/s
Prefill (avg)
447.41 tok/s
TTFT (avg)
0.67 s
VRAM (avg)
53.13 GB
MTP acceptance rate
—
TTFB
0.89 GB
Power draw
75 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
Q5_K_S
Framework
Ollama
Version
v0.46
Context length
16384 tokens
Batch size
256
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 M4 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
53.13 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
75 W

Sources & evidence

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

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

    v0.46 · macOS 15.0 · CUDA N/A · 16384 ctx

    111.59 tok/s

    Decode

    447.41 tok/s

    Prefill

    0.67 s

    TTFT

    53.13 GB

    VRAM

    —

    MTP

    75 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=26 running model_id=50 at Q5_K_S