Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q2_K

Start a discussion
AMD Radeon RX 9070 GRE12GBllama.cpp v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q2_K) on AMD Radeon RX 9070 GRE with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

298.41 tok/s

Decode

Decode speed

1,440.77 tok/s

Prefill

Prefill speed

0.88 s

TTFT

Time to first token

2.79 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 · IQ3_S Decode 241.94 · Prefill 776.44 ·
  2. llama.cpp · Q2_K (current)Decode 298.41 · Prefill 1440.77 ·

Core figures

Decode (avg)
298.41 tok/s
Prefill (avg)
1,440.77 tok/s
TTFT (avg)
0.88 s
VRAM (avg)
2.79 GB
MTP acceptance rate
—
TTFB
2.39 GB
Power draw
222.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.20
Context length
32768 tokens
Batch size
512
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 RX 9070 GRE
Nominal VRAM
12 GB
Measured VRAM (avg)
2.79 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
222.9 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

    v0.20 · Ubuntu 22.04 · CUDA N/A · 32768 ctx

    298.41 tok/s

    Decode

    1,440.77 tok/s

    Prefill

    0.88 s

    TTFT

    2.79 GB

    VRAM

    —

    MTP

    222.9 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=32 running model_id=62 at Q2_K