Arao AI
Back to search results

Qwen3.6-35B-A3B · Q4_K_S

Start a discussion
Apple M4 Max128GBllama.cpp v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-35B-A3B (Q4_K_S) on Apple M4 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

111.01 tok/s

Decode

Decode speed

387.61 tok/s

Prefill

Prefill speed

2.26 s

TTFT

Time to first token

59.43 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_XS Decode 121.63 · Prefill 540.05 ·
  2. llama.cpp · Q4_K_S (current)Decode 111.01 · Prefill 387.61 ·
  3. Ollama · Q3_K_L Decode 102.3 · Prefill 395.71 ·

Core figures

Decode (avg)
111.01 tok/s
Prefill (avg)
387.61 tok/s
TTFT (avg)
2.26 s
VRAM (avg)
59.43 GB
MTP acceptance rate
—
TTFB
0.89 GB
Power draw
47.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-35B-A3B
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.46
Context length
2048 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)
59.43 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
47.2 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

    v0.46 · macOS 15.0 · CUDA N/A · 2048 ctx

    111.01 tok/s

    Decode

    387.61 tok/s

    Prefill

    2.26 s

    TTFT

    59.43 GB

    VRAM

    —

    MTP

    47.2 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=26 running model_id=47 at Q4_K_S