Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ2_XS

Start a discussion
AMD Radeon AI PRO R970032GBllama.cpp v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ2_XS) on AMD Radeon AI PRO R9700 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

354.83 tok/s

Decode

Decode speed

1,505.4 tok/s

Prefill

Prefill speed

2.1 s

TTFT

Time to first token

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

Core figures

Decode (avg)
354.83 tok/s
Prefill (avg)
1,505.4 tok/s
TTFT (avg)
2.1 s
VRAM (avg)
2.71 GB
MTP acceptance rate
—
TTFB
2.84 GB
Power draw
221.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.46
Context length
16384 tokens
Batch size
256
GPU layers
20
Flash Attention
On

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)
2.71 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
221.5 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

    v0.46 · Ubuntu 22.04 · CUDA N/A · 16384 ctx

    354.83 tok/s

    Decode

    1,505.4 tok/s

    Prefill

    2.1 s

    TTFT

    2.71 GB

    VRAM

    —

    MTP

    221.5 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=79 running model_id=62 at IQ2_XS