Arao AI
Back to search results

Qwen3-8B · IQ1_S

Start a discussion
AMD Radeon AI PRO R970032GBStrata v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ1_S) on AMD Radeon AI PRO R9700 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

246.4 tok/s

Decode

Decode speed

1,052.77 tok/s

Prefill

Prefill speed

0.54 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

5 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 154.04 · Prefill 793.94 ·
  2. llama.cpp · Q3_K_S Decode 137.81 · Prefill 521.21 ·
  3. Strata · IQ1_S (current)Decode 246.4 · Prefill 1052.77 ·
  4. Strata · IQ3_XS Decode 190.7 · Prefill 730.63 ·

Core figures

Decode (avg)
246.4 tok/s
Prefill (avg)
1,052.77 tok/s
TTFT (avg)
0.54 s
VRAM (avg)
9.16 GB
MTP acceptance rate
0.72
TTFB
1.97 GB
Power draw
282 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ1_S
Framework
Strata
Version
v0.23
Context length
2048 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 Radeon AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
9.16 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
282 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.23 · Windows 11 23H2 · CUDA N/A · 2048 ctx

    246.4 tok/s

    Decode

    1,052.77 tok/s

    Prefill

    0.54 s

    TTFT

    9.16 GB

    VRAM

    0.72

    MTP

    282 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=79 running model_id=53 at IQ1_S