Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ3_S

Start a discussion
AMD Strix Halo (Radeon 8060S)Strata v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ3_S) on AMD Strix Halo (Radeon 8060S) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

374.22 tok/s

Decode

Decode speed

1,937.23 tok/s

Prefill

Prefill speed

0.42 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

2 days ago

Last verified

Performance

  1. vLLM · IQ2_XS Decode 355.91 · Prefill 1759.4 ·
  2. vLLM · IQ3_S Decode 267.01 · Prefill 1239.81 ·
  3. Strata · IQ3_S (current)Decode 374.22 · Prefill 1937.23 ·

Core figures

Decode (avg)
374.22 tok/s
Prefill (avg)
1,937.23 tok/s
TTFT (avg)
0.42 s
VRAM (avg)
2.93 GB
MTP acceptance rate
0.54
TTFB
2.99 GB
Power draw
68 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ3_S
Framework
Strata
Version
v0.29
Context length
2048 tokens
Batch size
512
GPU layers
5
Flash Attention
On

Hardware

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

GPU
AMD Strix Halo (Radeon 8060S)
Measured VRAM (avg)
2.93 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
N/A
Power draw
68 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.29 · Ubuntu 22.04 · CUDA N/A · 2048 ctx

    374.22 tok/s

    Decode

    1,937.23 tok/s

    Prefill

    0.42 s

    TTFT

    2.93 GB

    VRAM

    0.54

    MTP

    68 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=87 running model_id=62 at IQ3_S