Arao AI
Back to search results

Qwen3-Embedding-0.6B · FP16

Start a discussion
2x AMD Strix HaloOllama v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (FP16) on 2x AMD Strix Halo with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

181.91 tok/s

Decode

Decode speed

736.26 tok/s

Prefill

Prefill speed

2 s

TTFT

Time to first token

4.43 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · FP16 (current)Decode 181.91 · Prefill 736.26 ·
  2. Ollama · IQ4_XS Decode 379.81 · Prefill 1812.54 ·
  3. Strata · IQ4_XS Decode 288.7 · Prefill 1574.67 ·

Core figures

Decode (avg)
181.91 tok/s
Prefill (avg)
736.26 tok/s
TTFT (avg)
2 s
VRAM (avg)
4.43 GB
MTP acceptance rate
—
TTFB
1.46 GB
Power draw
97.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
FP16
Framework
Ollama
Version
v0.20
Context length
16384 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
2x AMD Strix Halo
Measured VRAM (avg)
4.43 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
N/A
Power draw
97.9 W

Sources & evidence

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

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

    v0.20 · Ubuntu 24.04 · CUDA N/A · 16384 ctx

    181.91 tok/s

    Decode

    736.26 tok/s

    Prefill

    2 s

    TTFT

    4.43 GB

    VRAM

    —

    MTP

    97.9 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=88 running model_id=62 at FP16