Arao AI
Back to search results

Qwen3.6-27B · IQ2_XS

Start a discussion
Apple M4 Max128GBllama.cpp v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-27B (IQ2_XS) on Apple M4 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

191.16 tok/s

Decode

Decode speed

1,032.54 tok/s

Prefill

Prefill speed

2.2 s

TTFT

Time to first token

29.32 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 189.88 · Prefill 951.61 ·
  2. llama.cpp · IQ2_XS (current)Decode 191.16 · Prefill 1032.54 ·
  3. vLLM · Q3_K_M Decode 174.24 · Prefill 673.46 ·
  4. Ollama · Q6_K Decode 99.52 · Prefill 397.09 ·

Core figures

Decode (avg)
191.16 tok/s
Prefill (avg)
1,032.54 tok/s
TTFT (avg)
2.2 s
VRAM (avg)
29.32 GB
MTP acceptance rate
—
TTFB
1.53 GB
Power draw
38.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-27B
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.39
Context length
32768 tokens
Batch size
512
GPU layers
99
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)
29.32 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
38.7 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

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

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

    v0.39 · macOS 15.0 · CUDA N/A · 32768 ctx

    191.16 tok/s

    Decode

    1,032.54 tok/s

    Prefill

    2.2 s

    TTFT

    29.32 GB

    VRAM

    —

    MTP

    38.7 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=26 running model_id=6 at IQ2_XS