Arao AI
Back to search results

Qwen3.5-9B · Q4_K_S

Start a discussion
AMD Ryzen AI Max+ 395128GBOllama v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-9B (Q4_K_S) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

85.51 tok/s

Decode

Decode speed

324.93 tok/s

Prefill

Prefill speed

1.46 s

TTFT

Time to first token

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

Core figures

Decode (avg)
85.51 tok/s
Prefill (avg)
324.93 tok/s
TTFT (avg)
1.46 s
VRAM (avg)
16.84 GB
MTP acceptance rate
—
TTFB
0.68 GB
Power draw
67.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-9B
Quantization
Q4_K_S
Framework
Ollama
Version
v0.54
Context length
16384 tokens
Batch size
512
GPU layers
33
Flash Attention
Off

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)
16.84 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
N/A
Power draw
67.9 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

    v0.54 · Ubuntu 22.04 · CUDA N/A · 16384 ctx

    85.51 tok/s

    Decode

    324.93 tok/s

    Prefill

    1.46 s

    TTFT

    16.84 GB

    VRAM

    —

    MTP

    67.9 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=24 running model_id=49 at Q4_K_S