Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q2_K

Start a discussion
Apple M2 UltravLLM v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q2_K) on Apple M2 Ultra with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

308 tok/s

Decode

Decode speed

1,290.58 tok/s

Prefill

Prefill speed

1.45 s

TTFT

Time to first token

2.79 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 · FP16 Decode 152.68 · Prefill 595.8 ·
  2. vLLM · Q2_K (current)Decode 308 · Prefill 1290.58 ·
  3. Strata · IQ3_XS Decode 284.88 · Prefill 1247.89 ·

Core figures

Decode (avg)
308 tok/s
Prefill (avg)
1,290.58 tok/s
TTFT (avg)
1.45 s
VRAM (avg)
2.79 GB
MTP acceptance rate
—
TTFB
2.46 GB
Power draw
66.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q2_K
Framework
vLLM
Version
v0.33
Context length
16384 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 M2 Ultra
Measured VRAM (avg)
2.79 GB
OS
macOS 15.0
Driver
Apple M2 Ultra
CUDA
N/A
Power draw
66.9 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

    v0.33 · macOS 15.0 · CUDA N/A · 16384 ctx

    308 tok/s

    Decode

    1,290.58 tok/s

    Prefill

    1.45 s

    TTFT

    2.79 GB

    VRAM

    —

    MTP

    66.9 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=103 running model_id=62 at Q2_K