Arao AI
Back to search results

Qwen3.5-27B · Q3_K_S

Start a discussion
AMD Ryzen AI Max+ 395128GBOllama v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (Q3_K_S) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

82.93 tok/s

Decode

Decode speed

370 tok/s

Prefill

Prefill speed

0.82 s

TTFT

Time to first token

38.96 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · IQ1_S Decode 109.46 · Prefill 421.76 ·
  2. Ollama · Q3_K_S (current)Decode 82.93 · Prefill 370 ·
  3. Strata · Q3_K_L Decode 119.77 · Prefill 539.8 ·
  4. Strata · Q4_K_M Decode 114.2 · Prefill 433.75 ·

Core figures

Decode (avg)
82.93 tok/s
Prefill (avg)
370 tok/s
TTFT (avg)
0.82 s
VRAM (avg)
38.96 GB
MTP acceptance rate
—
TTFB
0.66 GB
Power draw
114.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
Q3_K_S
Framework
Ollama
Version
v0.43
Context length
8192 tokens
Batch size
256
GPU layers
28
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)
38.96 GB
OS
Windows 11 23H2
Driver
amdgpu 6.10
CUDA
N/A
Power draw
114.7 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

    v0.43 · Windows 11 23H2 · CUDA N/A · 8192 ctx

    82.93 tok/s

    Decode

    370 tok/s

    Prefill

    0.82 s

    TTFT

    38.96 GB

    VRAM

    —

    MTP

    114.7 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=24 running model_id=50 at Q3_K_S