Arao AI
Back to search results

Qwen3.5-9B · IQ3_XS

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-9B (IQ3_XS) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

115.94 tok/s

Decode

Decode speed

451.93 tok/s

Prefill

Prefill speed

0.72 s

TTFT

Time to first token

13.82 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 · IQ3_XS (current)Decode 115.94 · Prefill 451.93 ·
  2. vLLM · Q5_K_M Decode 83.86 · Prefill 287.36 ·
  3. Ollama · Q4_K_S Decode 85.51 · Prefill 324.93 ·
  4. llama.cpp · IQ3_XS Decode 118.29 · Prefill 392.28 ·

Core figures

Decode (avg)
115.94 tok/s
Prefill (avg)
451.93 tok/s
TTFT (avg)
0.72 s
VRAM (avg)
13.82 GB
MTP acceptance rate
—
TTFB
0.93 GB
Power draw
66.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-9B
Quantization
IQ3_XS
Framework
vLLM
Version
v0.37
Context length
2048 tokens
Batch size
16
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)
13.82 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
66.9 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

    v0.37 · Ubuntu 22.04 · CUDA N/A · 2048 ctx

    115.94 tok/s

    Decode

    451.93 tok/s

    Prefill

    0.72 s

    TTFT

    13.82 GB

    VRAM

    —

    MTP

    66.9 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=24 running model_id=49 at IQ3_XS