Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q5_K_M

Start a discussion
AMD Radeon RX 9070 XT16GBvLLM v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q5_K_M) on AMD Radeon RX 9070 XT with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

254.02 tok/s

Decode

Decode speed

1,313.89 tok/s

Prefill

Prefill speed

1.37 s

TTFT

Time to first token

3.28 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 308.65 · Prefill 1242.43 ·
  2. llama.cpp · Q4_K_S Decode 280.71 · Prefill 1416.08 ·
  3. vLLM · IQ1_S Decode 320.75 · Prefill 1355.61 ·
  4. vLLM · Q5_K_M (current)Decode 254.02 · Prefill 1313.89 ·

Core figures

Decode (avg)
254.02 tok/s
Prefill (avg)
1,313.89 tok/s
TTFT (avg)
1.37 s
VRAM (avg)
3.28 GB
MTP acceptance rate
—
TTFB
2.03 GB
Power draw
224 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q5_K_M
Framework
vLLM
Version
v0.42
Context length
16384 tokens
Batch size
16
GPU layers
999
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 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
3.28 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
224 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

    v0.42 · Ubuntu 22.04 · CUDA N/A · 16384 ctx

    254.02 tok/s

    Decode

    1,313.89 tok/s

    Prefill

    1.37 s

    TTFT

    3.28 GB

    VRAM

    —

    MTP

    224 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=16 running model_id=62 at Q5_K_M