Arao AI
Back to search results

Qwen3.5-27B · Q4_K_M

Start a discussion
AMD Ryzen AI Max+ 395128GBStrata v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (Q4_K_M) on AMD Ryzen AI Max+ 395 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

114.2 tok/s

Decode

Decode speed

433.75 tok/s

Prefill

Prefill speed

0.69 s

TTFT

Time to first token

48.59 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 Decode 82.93 · Prefill 370 ·
  3. Strata · Q3_K_L Decode 119.77 · Prefill 539.8 ·
  4. Strata · Q4_K_M (current)Decode 114.2 · Prefill 433.75 ·

Core figures

Decode (avg)
114.2 tok/s
Prefill (avg)
433.75 tok/s
TTFT (avg)
0.69 s
VRAM (avg)
48.59 GB
MTP acceptance rate
0.71
TTFB
0.91 GB
Power draw
116.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
Q4_K_M
Framework
Strata
Version
v0.34
Context length
32768 tokens
Batch size
1024
GPU layers
5
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)
48.59 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
N/A
Power draw
116.3 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

    v0.34 · Ubuntu 24.04 · CUDA N/A · 32768 ctx

    114.2 tok/s

    Decode

    433.75 tok/s

    Prefill

    0.69 s

    TTFT

    48.59 GB

    VRAM

    0.71

    MTP

    116.3 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=24 running model_id=50 at Q4_K_M