Arao AI
Back to search results

Qwen3-1.7B · Q2_K

Start a discussion
Apple M4 Pro64GBStrata v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q2_K) on Apple M4 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

389.55 tok/s

Decode

Decode speed

1,966.41 tok/s

Prefill

Prefill speed

2.42 s

TTFT

Time to first token

4.06 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Strata · Q2_K (current)Decode 389.55 · Prefill 1966.41 ·

Core figures

Decode (avg)
389.55 tok/s
Prefill (avg)
1,966.41 tok/s
TTFT (avg)
2.42 s
VRAM (avg)
4.06 GB
MTP acceptance rate
0.53
TTFB
3.12 GB
Power draw
48.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q2_K
Framework
Strata
Version
v0.35
Context length
8192 tokens
Batch size
1024
GPU layers
8
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
Apple M4 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
4.06 GB
OS
macOS 15.0
Driver
Apple M4 Pro
CUDA
N/A
Power draw
48.8 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.35 · macOS 15.0 · CUDA N/A · 8192 ctx

    389.55 tok/s

    Decode

    1,966.41 tok/s

    Prefill

    2.42 s

    TTFT

    4.06 GB

    VRAM

    0.53

    MTP

    48.8 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=25 running model_id=55 at Q2_K