Arao AI
Back to search results

Qwen3.8-9B · Q3_K_S

Start a discussion
AMD Radeon AI PRO R970032GBOllama v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_S) on AMD Radeon AI PRO R9700 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

110.64 tok/s

Decode

Decode speed

546.12 tok/s

Prefill

Prefill speed

2.31 s

TTFT

Time to first token

14.38 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · Q3_K_M Decode 123.24 · Prefill 659.52 ·
  2. Ollama · Q3_K_S (current)Decode 110.64 · Prefill 546.12 ·

Core figures

Decode (avg)
110.64 tok/s
Prefill (avg)
546.12 tok/s
TTFT (avg)
2.31 s
VRAM (avg)
14.38 GB
MTP acceptance rate
—
TTFB
0.89 GB
Power draw
304 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
Q3_K_S
Framework
Ollama
Version
v0.42
Context length
32768 tokens
Batch size
256
GPU layers
33
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)
14.38 GB
OS
macOS 15.0
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
304 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

    v0.42 · macOS 15.0 · CUDA N/A · 32768 ctx

    110.64 tok/s

    Decode

    546.12 tok/s

    Prefill

    2.31 s

    TTFT

    14.38 GB

    VRAM

    —

    MTP

    304 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=79 running model_id=52 at Q3_K_S