Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ4_XS

Start a discussion
Apple M1llama.cpp v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ4_XS) on Apple M1 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

148.84 tok/s

Decode

Decode speed

610.28 tok/s

Prefill

Prefill speed

1.99 s

TTFT

Time to first token

3.03 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ4_XS (current)Decode 148.84 · Prefill 610.28 ·
  2. Ollama · Q2_K Decode 166.63 · Prefill 805.73 ·

Core figures

Decode (avg)
148.84 tok/s
Prefill (avg)
610.28 tok/s
TTFT (avg)
1.99 s
VRAM (avg)
3.03 GB
MTP acceptance rate
—
TTFB
1.19 GB
Power draw
34.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ4_XS
Framework
llama.cpp
Version
v0.38
Context length
8192 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

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

GPU
Apple M1
Measured VRAM (avg)
3.03 GB
OS
macOS 15.0
Driver
Apple M1
CUDA
N/A
Power draw
34.3 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

    v0.38 · macOS 15.0 · CUDA N/A · 8192 ctx

    148.84 tok/s

    Decode

    610.28 tok/s

    Prefill

    1.99 s

    TTFT

    3.03 GB

    VRAM

    —

    MTP

    34.3 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=99 running model_id=62 at IQ4_XS