Arao AI
Back to search results

Qwen3-8B · IQ1_S

Start a discussion
AMD Strix Point (Radeon 890M)Strata v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ1_S) on AMD Strix Point (Radeon 890M) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

121.73 tok/s

Decode

Decode speed

484.23 tok/s

Prefill

Prefill speed

1.34 s

TTFT

Time to first token

9.16 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_M Decode 56.8 · Prefill 217.7 ·
  2. Strata · IQ1_S (current)Decode 121.73 · Prefill 484.23 ·
  3. Strata · Q5_K_S Decode 66.77 · Prefill 312.73 ·

Core figures

Decode (avg)
121.73 tok/s
Prefill (avg)
484.23 tok/s
TTFT (avg)
1.34 s
VRAM (avg)
9.16 GB
MTP acceptance rate
0.52
TTFB
0.97 GB
Power draw
56.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ1_S
Framework
Strata
Version
v0.26
Context length
8192 tokens
Batch size
512
GPU layers
12
Flash Attention
On

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)
9.16 GB
OS
macOS 15.0
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
56.3 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

    v0.26 · macOS 15.0 · CUDA N/A · 8192 ctx

    121.73 tok/s

    Decode

    484.23 tok/s

    Prefill

    1.34 s

    TTFT

    9.16 GB

    VRAM

    0.52

    MTP

    56.3 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=89 running model_id=53 at IQ1_S