Arao AI
Back to search results

Qwen3-8B · IQ3_S

Start a discussion
AMD Ryzen AI Max+ 395128GBOllama v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ3_S) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

106.51 tok/s

Decode

Decode speed

487.62 tok/s

Prefill

Prefill speed

0.14 s

TTFT

Time to first token

13.19 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 · FP16 Decode 52.16 · Prefill 223.09 ·
  2. llama.cpp · Q8_0 Decode 70.95 · Prefill 365.06 ·
  3. vLLM · IQ3_S Decode 125.05 · Prefill 672.6 ·
  4. Ollama · IQ3_S (current)Decode 106.51 · Prefill 487.62 ·

Core figures

Decode (avg)
106.51 tok/s
Prefill (avg)
487.62 tok/s
TTFT (avg)
0.14 s
VRAM (avg)
13.19 GB
MTP acceptance rate
—
TTFB
0.85 GB
Power draw
58 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ3_S
Framework
Ollama
Version
v0.48
Context length
16384 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
AMD Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
13.19 GB
OS
Windows 11 23H2
Driver
AMD Adrenalin 25.10.1
CUDA
N/A
Power draw
58 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

    v0.48 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    106.51 tok/s

    Decode

    487.62 tok/s

    Prefill

    0.14 s

    TTFT

    13.19 GB

    VRAM

    —

    MTP

    58 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=24 running model_id=53 at IQ3_S