Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ4_XS

Start a discussion
AMD Radeon RX 907016GBllama.cpp v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ4_XS) on AMD Radeon RX 9070 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

254.94 tok/s

Decode

Decode speed

1,358.71 tok/s

Prefill

Prefill speed

0.44 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 · IQ4_XS (current)Decode 254.94 · Prefill 1358.71 ·
  2. llama.cpp · Q5_K_M Decode 203.72 · Prefill 927.46 ·
  3. Strata · Q3_K_M Decode 383.87 · Prefill 1815.17 ·

Core figures

Decode (avg)
254.94 tok/s
Prefill (avg)
1,358.71 tok/s
TTFT (avg)
0.44 s
VRAM (avg)
3.03 GB
MTP acceptance rate
—
TTFB
2.04 GB
Power draw
239.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ4_XS
Framework
llama.cpp
Version
v0.22
Context length
2048 tokens
Batch size
256
GPU layers
28
Flash Attention
Off

Hardware

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

GPU
AMD Radeon RX 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
3.03 GB
OS
Windows 11 23H2
Driver
amdgpu 6.10
CUDA
N/A
Power draw
239.9 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.22 · Windows 11 23H2 · CUDA N/A · 2048 ctx

    254.94 tok/s

    Decode

    1,358.71 tok/s

    Prefill

    0.44 s

    TTFT

    3.03 GB

    VRAM

    —

    MTP

    239.9 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=21 running model_id=62 at IQ4_XS