Arao AI
Back to search results

Qwen3.5-27B · Q6_K

Start a discussion
Apple M1 MaxvLLM v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (Q6_K) on Apple M1 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

47.77 tok/s

Decode

Decode speed

232.57 tok/s

Prefill

Prefill speed

0.52 s

TTFT

Time to first token

58.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · Q6_K (current)Decode 47.77 · Prefill 232.57 ·

Core figures

Decode (avg)
47.77 tok/s
Prefill (avg)
232.57 tok/s
TTFT (avg)
0.52 s
VRAM (avg)
58.8 GB
MTP acceptance rate
—
TTFB
0.38 GB
Power draw
40.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
Q6_K
Framework
vLLM
Version
v0.30
Context length
8192 tokens
Batch size
8
GPU layers
999
Flash Attention
On

Hardware

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

GPU
Apple M1 Max
Measured VRAM (avg)
58.8 GB
OS
macOS 15.0
Driver
Apple M1 Max
CUDA
N/A
Power draw
40.9 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.30 · macOS 15.0 · CUDA N/A · 8192 ctx

    47.77 tok/s

    Decode

    232.57 tok/s

    Prefill

    0.52 s

    TTFT

    58.8 GB

    VRAM

    —

    MTP

    40.9 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=101 running model_id=50 at Q6_K