Arao AI
Back to search results

Qwen3.6-27B · FP16

Start a discussion
AMD Ryzen AI Max+ 395128GBOllama v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-27B (FP16) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

12 tok/s

Decode

Decode speed

64.43 tok/s

Prefill

Prefill speed

1.25 s

TTFT

Time to first token

107 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 Decode 27.72 · Prefill 124.12 ·
  2. Ollama · FP16 (current)Decode 12 · Prefill 64.43 ·

Core figures

Decode (avg)
12 tok/s
Prefill (avg)
64.43 tok/s
TTFT (avg)
1.25 s
VRAM (avg)
107 GB
MTP acceptance rate
—
TTFB
0.1 GB
Power draw
56.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-27B
Quantization
FP16
Framework
Ollama
Version
v0.21
Context length
2048 tokens
Batch size
256
GPU layers
20
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)
107 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.12
CUDA
12.6
Power draw
56.9 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

    v0.21 · Ubuntu 22.04 · CUDA 12.6 · 2048 ctx

    12 tok/s

    Decode

    64.43 tok/s

    Prefill

    1.25 s

    TTFT

    107 GB

    VRAM

    —

    MTP

    56.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=24 running model_id=6 at FP16