Arao AI
Back to search results

Qwen3-Coder-Next · IQ4_XS

Start a discussion
Apple M1 MaxOllama v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ4_XS) on Apple M1 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

76.5 tok/s

Decode

Decode speed

413.9 tok/s

Prefill

Prefill speed

1.07 s

TTFT

Time to first token

1.05 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · IQ4_XS (current)Decode 76.5 · Prefill 413.9 ·
  2. Strata · IQ2_M Decode 143.28 · Prefill 613.22 ·

Core figures

Decode (avg)
76.5 tok/s
Prefill (avg)
413.9 tok/s
TTFT (avg)
1.07 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.61 GB
Power draw
45.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
IQ4_XS
Framework
Ollama
Version
v0.39
Context length
16384 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 M1 Max
Measured VRAM (avg)
1.05 GB
OS
macOS 15.0
Driver
Apple M1 Max
CUDA
N/A
Power draw
45.3 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

    v0.39 · macOS 15.0 · CUDA N/A · 16384 ctx

    76.5 tok/s

    Decode

    413.9 tok/s

    Prefill

    1.07 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    45.3 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=101 running model_id=58 at IQ4_XS