Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ4_XS

Start a discussion
AMD Radeon AI PRO R970032GBllama.cpp v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ4_XS) on AMD Radeon AI PRO R9700 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

342.35 tok/s

Decode

Decode speed

1,387.76 tok/s

Prefill

Prefill speed

1.24 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

5 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS Decode 354.83 · Prefill 1505.4 ·
  2. llama.cpp · IQ4_XS (current)Decode 342.35 · Prefill 1387.76 ·

Core figures

Decode (avg)
342.35 tok/s
Prefill (avg)
1,387.76 tok/s
TTFT (avg)
1.24 s
VRAM (avg)
3.03 GB
MTP acceptance rate
—
TTFB
2.74 GB
Power draw
239.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ4_XS
Framework
llama.cpp
Version
v0.23
Context length
8192 tokens
Batch size
512
GPU layers
99
Flash Attention
Off

Hardware

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

GPU
AMD Radeon AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
3.03 GB
OS
macOS 15.0
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
239.5 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

    v0.23 · macOS 15.0 · CUDA N/A · 8192 ctx

    342.35 tok/s

    Decode

    1,387.76 tok/s

    Prefill

    1.24 s

    TTFT

    3.03 GB

    VRAM

    —

    MTP

    239.5 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=79 running model_id=62 at IQ4_XS