Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ3_XS

Start a discussion
AMD Strix Point (Radeon 890M)Strata v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ3_XS) on AMD Strix Point (Radeon 890M) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

273.43 tok/s

Decode

Decode speed

1,002.15 tok/s

Prefill

Prefill speed

1.81 s

TTFT

Time to first token

2.88 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 · Q4_K_S Decode 178.08 · Prefill 918.71 ·
  2. vLLM · Q8_0 Decode 112.43 · Prefill 505.72 ·
  3. Strata · IQ2_M Decode 281.13 · Prefill 1305.8 ·
  4. Strata · IQ3_XS (current)Decode 273.43 · Prefill 1002.15 ·

Core figures

Decode (avg)
273.43 tok/s
Prefill (avg)
1,002.15 tok/s
TTFT (avg)
1.81 s
VRAM (avg)
2.88 GB
MTP acceptance rate
0.73
TTFB
2.19 GB
Power draw
56.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ3_XS
Framework
Strata
Version
v0.52
Context length
4096 tokens
Batch size
1024
GPU layers
8
Flash Attention
Off

Hardware

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

GPU
AMD Strix Point (Radeon 890M)
Measured VRAM (avg)
2.88 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
N/A
Power draw
56.2 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

    v0.52 · Windows 11 23H2 · CUDA N/A · 4096 ctx

    273.43 tok/s

    Decode

    1,002.15 tok/s

    Prefill

    1.81 s

    TTFT

    2.88 GB

    VRAM

    0.73

    MTP

    56.2 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=89 running model_id=62 at IQ3_XS