Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ3_S

Start a discussion
AMD Radeon RX 7800 XT16GBvLLM v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ3_S) on AMD Radeon RX 7800 XT with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

270.28 tok/s

Decode

Decode speed

1,137.75 tok/s

Prefill

Prefill speed

0.25 s

TTFT

Time to first token

2.93 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · IQ3_S (current)Decode 270.28 · Prefill 1137.75 ·
  2. Strata · Q3_K_L Decode 363.34 · Prefill 1209.51 ·
  3. Strata · Q5_K_S Decode 288.93 · Prefill 1097.54 ·

Core figures

Decode (avg)
270.28 tok/s
Prefill (avg)
1,137.75 tok/s
TTFT (avg)
0.25 s
VRAM (avg)
2.93 GB
MTP acceptance rate
—
TTFB
2.16 GB
Power draw
266 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ3_S
Framework
vLLM
Version
v0.34
Context length
8192 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 7800 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
2.93 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
266 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

    v0.34 · Ubuntu 24.04 · CUDA N/A · 8192 ctx

    270.28 tok/s

    Decode

    1,137.75 tok/s

    Prefill

    0.25 s

    TTFT

    2.93 GB

    VRAM

    —

    MTP

    266 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=31 running model_id=62 at IQ3_S