Arao AI
Back to search results

Qwen3.6-27B · IQ3_XS

Start a discussion
AMD Ryzen AI Max+ 395128GBllama.cpp v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-27B (IQ3_XS) on AMD Ryzen AI Max+ 395 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

27.72 tok/s

Decode

Decode speed

124.12 tok/s

Prefill

Prefill speed

1.55 s

TTFT

Time to first token

37.25 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · IQ3_XS (current)Decode 27.72 · Prefill 124.12 ·
  2. Ollama · FP16 Decode 12 · Prefill 64.43 ·

Core figures

Decode (avg)
27.72 tok/s
Prefill (avg)
124.12 tok/s
TTFT (avg)
1.55 s
VRAM (avg)
37.25 GB
MTP acceptance rate
—
TTFB
0.22 GB
Power draw
69.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-27B
Quantization
IQ3_XS
Framework
llama.cpp
Version
v0.22
Context length
2048 tokens
Batch size
512
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)
37.25 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
12.8
Power draw
69.7 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.22 · Windows 11 23H2 · CUDA 12.8 · 2048 ctx

    27.72 tok/s

    Decode

    124.12 tok/s

    Prefill

    1.55 s

    TTFT

    37.25 GB

    VRAM

    —

    MTP

    69.7 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=24 running model_id=6 at IQ3_XS