Arao AI
Back to search results

Qwen3.5-35B-A3B · IQ4_XS

Start a discussion
Apple M4 Max128GBvLLM v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-35B-A3B (IQ4_XS) on Apple M4 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

115.28 tok/s

Decode

Decode speed

541.34 tok/s

Prefill

Prefill speed

1.41 s

TTFT

Time to first token

58.04 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ4_XS (current)Decode 115.28 · Prefill 541.34 ·
  2. vLLM · Q4_K_S Decode 115.9 · Prefill 629 ·
  3. Ollama · IQ2_XS Decode 138.01 · Prefill 631.53 ·

Core figures

Decode (avg)
115.28 tok/s
Prefill (avg)
541.34 tok/s
TTFT (avg)
1.41 s
VRAM (avg)
58.04 GB
MTP acceptance rate
—
TTFB
0.92 GB
Power draw
51.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-35B-A3B
Quantization
IQ4_XS
Framework
vLLM
Version
v0.28
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 M4 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
58.04 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
51.8 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

    v0.28 · macOS 15.0 · CUDA N/A · 8192 ctx

    115.28 tok/s

    Decode

    541.34 tok/s

    Prefill

    1.41 s

    TTFT

    58.04 GB

    VRAM

    —

    MTP

    51.8 W

    Power draw

    L2 batch seed 2026-10-10: vLLM on hw_id=26 running model_id=15 at IQ4_XS