Arao AI
Back to search results

Qwen3-1.7B · IQ3_S

Start a discussion
Apple M4 Max128GBvLLM v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (IQ3_S) on Apple M4 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

318.24 tok/s

Decode

Decode speed

1,490.26 tok/s

Prefill

Prefill speed

0.12 s

TTFT

Time to first token

4.45 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ3_S (current)Decode 318.24 · Prefill 1490.26 ·
  2. vLLM · Q5_K_S Decode 322.68 · Prefill 1251.16 ·
  3. Strata · IQ2_XS Decode 304.05 · Prefill 1416.13 ·

Core figures

Decode (avg)
318.24 tok/s
Prefill (avg)
1,490.26 tok/s
TTFT (avg)
0.12 s
VRAM (avg)
4.45 GB
MTP acceptance rate
—
TTFB
2.55 GB
Power draw
59.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
IQ3_S
Framework
vLLM
Version
v0.54
Context length
2048 tokens
Batch size
16
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)
4.45 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
59.2 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

    v0.54 · macOS 15.0 · CUDA N/A · 2048 ctx

    318.24 tok/s

    Decode

    1,490.26 tok/s

    Prefill

    0.12 s

    TTFT

    4.45 GB

    VRAM

    —

    MTP

    59.2 W

    Power draw

    L2 batch seed 2026-10-10: vLLM on hw_id=26 running model_id=55 at IQ3_S