Arao AI
Back to search results

Qwen3.5-27B · Q3_K_L

Start a discussion
AMD Ryzen AI Max+ 395128GBStrata v0.55L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (Q3_K_L) on AMD Ryzen AI Max+ 395 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

119.77 tok/s

Decode

Decode speed

539.8 tok/s

Prefill

Prefill speed

0.68 s

TTFT

Time to first token

42.92 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 (current)Decode 119.77 · Prefill 539.8 ·
  4. Strata · Q4_K_M Decode 114.2 · Prefill 433.75 ·

Core figures

Decode (avg)
119.77 tok/s
Prefill (avg)
539.8 tok/s
TTFT (avg)
0.68 s
VRAM (avg)
42.92 GB
MTP acceptance rate
0.6
TTFB
0.96 GB
Power draw
95.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
Q3_K_L
Framework
Strata
Version
v0.55
Context length
2048 tokens
Batch size
256
GPU layers
8
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)
42.92 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
N/A
Power draw
95.2 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

    v0.55 · Ubuntu 22.04 · CUDA N/A · 2048 ctx

    119.77 tok/s

    Decode

    539.8 tok/s

    Prefill

    0.68 s

    TTFT

    42.92 GB

    VRAM

    0.6

    MTP

    95.2 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=24 running model_id=50 at Q3_K_L