Arao AI
Back to search results

Qwen3-Embedding-0.6B · FP16

Start a discussion
Apple M2 UltravLLM v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (FP16) on Apple M2 Ultra with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

152.68 tok/s

Decode

Decode speed

595.8 tok/s

Prefill

Prefill speed

1.83 s

TTFT

Time to first token

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

Core figures

Decode (avg)
152.68 tok/s
Prefill (avg)
595.8 tok/s
TTFT (avg)
1.83 s
VRAM (avg)
4.43 GB
MTP acceptance rate
—
TTFB
1.22 GB
Power draw
57.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
FP16
Framework
vLLM
Version
v0.30
Context length
4096 tokens
Batch size
32
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)
4.43 GB
OS
macOS 15.0
Driver
Apple M2 Ultra
CUDA
N/A
Power draw
57.6 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

    v0.30 · macOS 15.0 · CUDA N/A · 4096 ctx

    152.68 tok/s

    Decode

    595.8 tok/s

    Prefill

    1.83 s

    TTFT

    4.43 GB

    VRAM

    —

    MTP

    57.6 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=103 running model_id=62 at FP16