Arao AI
Back to search results

Qwen3-Coder-Next · IQ1_S

Start a discussion
Apple M2 UltravLLM v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ1_S) on Apple M2 Ultra with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

161.77 tok/s

Decode

Decode speed

872.93 tok/s

Prefill

Prefill speed

1.37 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. llama.cpp · Q4_K_S Decode 104.58 · Prefill 471.99 ·
  2. vLLM · IQ1_S (current)Decode 161.77 · Prefill 872.93 ·
  3. vLLM · Q5_K_S Decode 96.07 · Prefill 412.07 ·

Core figures

Decode (avg)
161.77 tok/s
Prefill (avg)
872.93 tok/s
TTFT (avg)
1.37 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
1.29 GB
Power draw
69.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
IQ1_S
Framework
vLLM
Version
v0.52
Context length
2048 tokens
Batch size
32
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 M2 Ultra
Measured VRAM (avg)
1.05 GB
OS
macOS 15.0
Driver
Apple M2 Ultra
CUDA
N/A
Power draw
69.7 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

    v0.52 · macOS 15.0 · CUDA N/A · 2048 ctx

    161.77 tok/s

    Decode

    872.93 tok/s

    Prefill

    1.37 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    69.7 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=103 running model_id=58 at IQ1_S