Arao AI
Back to search results

Qwen3-1.7B · Q4_K_S

Start a discussion
Apple M1 MaxvLLM v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_S) on Apple M1 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

157.62 tok/s

Decode

Decode speed

743.87 tok/s

Prefill

Prefill speed

1.15 s

TTFT

Time to first token

4.88 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · Q4_K_S (current)Decode 157.62 · Prefill 743.87 ·
  2. Strata · IQ4_XS Decode 217.54 · Prefill 1114.27 ·
  3. Strata · Q6_K Decode 152.31 · Prefill 609.9 ·

Core figures

Decode (avg)
157.62 tok/s
Prefill (avg)
743.87 tok/s
TTFT (avg)
1.15 s
VRAM (avg)
4.88 GB
MTP acceptance rate
—
TTFB
1.26 GB
Power draw
55.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
Q4_K_S
Framework
vLLM
Version
v0.54
Context length
4096 tokens
Batch size
16
GPU layers
999
Flash Attention
Off

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)
4.88 GB
OS
macOS 15.0
Driver
Apple M1 Max
CUDA
N/A
Power draw
55.4 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

    v0.54 · macOS 15.0 · CUDA N/A · 4096 ctx

    157.62 tok/s

    Decode

    743.87 tok/s

    Prefill

    1.15 s

    TTFT

    4.88 GB

    VRAM

    —

    MTP

    55.4 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=101 running model_id=55 at Q4_K_S