Arao AI
Back to search results

Qwen3-8B · IQ3_S

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.24L2 Cross-framework verified

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

125.05 tok/s

Decode

Decode speed

672.6 tok/s

Prefill

Prefill speed

2.4 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

2 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 (current)Decode 125.05 · Prefill 672.6 ·
  4. Ollama · IQ3_S Decode 106.51 · Prefill 487.62 ·

Core figures

Decode (avg)
125.05 tok/s
Prefill (avg)
672.6 tok/s
TTFT (avg)
2.4 s
VRAM (avg)
13.19 GB
MTP acceptance rate
—
TTFB
1 GB
Power draw
69.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ3_S
Framework
vLLM
Version
v0.24
Context length
32768 tokens
Batch size
32
GPU layers
999
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
Ubuntu 24.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
69.7 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

    v0.24 · Ubuntu 24.04 · CUDA N/A · 32768 ctx

    125.05 tok/s

    Decode

    672.6 tok/s

    Prefill

    2.4 s

    TTFT

    13.19 GB

    VRAM

    —

    MTP

    69.7 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=24 running model_id=53 at IQ3_S