Arao AI
Back to search results

Qwen3.5-0.8B · IQ3_XS

Start a discussion
AMD Strix Point (Radeon 890M)vLLM v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_XS) on AMD Strix Point (Radeon 890M) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

172.31 tok/s

Decode

Decode speed

798.79 tok/s

Prefill

Prefill speed

1.52 s

TTFT

Time to first token

3.14 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 · IQ3_XS (current)Decode 172.31 · Prefill 798.79 ·
  2. Strata · Q5_K_M Decode 163.87 · Prefill 897.86 ·

Core figures

Decode (avg)
172.31 tok/s
Prefill (avg)
798.79 tok/s
TTFT (avg)
1.52 s
VRAM (avg)
3.14 GB
MTP acceptance rate
—
TTFB
1.38 GB
Power draw
74.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ3_XS
Framework
vLLM
Version
v0.42
Context length
4096 tokens
Batch size
16
GPU layers
999
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)
3.14 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
N/A
Power draw
74.4 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

    v0.42 · Ubuntu 24.04 · CUDA N/A · 4096 ctx

    172.31 tok/s

    Decode

    798.79 tok/s

    Prefill

    1.52 s

    TTFT

    3.14 GB

    VRAM

    —

    MTP

    74.4 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=89 running model_id=51 at IQ3_XS