Arao AI
Back to search results

Qwen3.5-27B · Q2_K

Start a discussion
Apple M3 Max36GBStrata v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (Q2_K) on Apple M3 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

150.5 tok/s

Decode

Decode speed

804.01 tok/s

Prefill

Prefill speed

2.44 s

TTFT

Time to first token

33.29 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Strata · Q2_K (current)Decode 150.5 · Prefill 804.01 ·

Core figures

Decode (avg)
150.5 tok/s
Prefill (avg)
804.01 tok/s
TTFT (avg)
2.44 s
VRAM (avg)
33.29 GB
MTP acceptance rate
0.5
TTFB
1.2 GB
Power draw
35.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
Q2_K
Framework
Strata
Version
v0.47
Context length
16384 tokens
Batch size
1024
GPU layers
15
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
Apple M3 Max
Nominal VRAM
36 GB
Measured VRAM (avg)
33.29 GB
OS
macOS 15.0
Driver
Apple M3 Max
CUDA
N/A
Power draw
35.2 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

    v0.47 · macOS 15.0 · CUDA N/A · 16384 ctx

    150.5 tok/s

    Decode

    804.01 tok/s

    Prefill

    2.44 s

    TTFT

    33.29 GB

    VRAM

    0.5

    MTP

    35.2 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=4 running model_id=50 at Q2_K