Arao AI
Back to search results

Qwen3-1.7B · IQ2_XS

Start a discussion
Apple M4 Max128GBStrata v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (IQ2_XS) on Apple M4 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

304.05 tok/s

Decode

Decode speed

1,416.13 tok/s

Prefill

Prefill speed

2.4 s

TTFT

Time to first token

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

Core figures

Decode (avg)
304.05 tok/s
Prefill (avg)
1,416.13 tok/s
TTFT (avg)
2.4 s
VRAM (avg)
3.81 GB
MTP acceptance rate
0.56
TTFB
2.43 GB
Power draw
62.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
IQ2_XS
Framework
Strata
Version
v0.41
Context length
2048 tokens
Batch size
1024
GPU layers
12
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)
3.81 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
62.8 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

    v0.41 · macOS 15.0 · CUDA N/A · 2048 ctx

    304.05 tok/s

    Decode

    1,416.13 tok/s

    Prefill

    2.4 s

    TTFT

    3.81 GB

    VRAM

    0.56

    MTP

    62.8 W

    Power draw

    L2 batch seed 2026-10-10: Strata on hw_id=26 running model_id=55 at IQ2_XS