Arao AI
Back to search results

Qwen3.5-27B · Q8_0

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-27B (Q8_0) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

18.22 tok/s

Decode

Decode speed

78.36 tok/s

Prefill

Prefill speed

0.25 s

TTFT

Time to first token

67.3 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · Q8_0 (current)Decode 18.22 · Prefill 78.36 ·
  2. Ollama · IQ3_S Decode 27.26 · Prefill 100.74 ·
  3. Ollama · Q6_K Decode 16.05 · Prefill 66.18 ·
  4. Ollama · IQ1_S Decode 109.46 · Prefill 421.76 ·
  5. Ollama · Q3_K_S Decode 82.93 · Prefill 370 ·
  6. Strata · Q3_K_L Decode 119.77 · Prefill 539.8 ·
  7. Strata · Q4_K_M Decode 114.2 · Prefill 433.75 ·

Core figures

Decode (avg)
18.22 tok/s
Prefill (avg)
78.36 tok/s
TTFT (avg)
0.25 s
VRAM (avg)
67.3 GB
MTP acceptance rate
—
TTFB
0.15 GB
Power draw
54.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
Q8_0
Framework
vLLM
Version
v0.47
Context length
4096 tokens
Batch size
32
GPU layers
999
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)
67.3 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
12.4
Power draw
54.9 W

Sources & evidence

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

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

    v0.47 · Ubuntu 22.04 · CUDA 12.4 · 4096 ctx

    18.22 tok/s

    Decode

    78.36 tok/s

    Prefill

    0.25 s

    TTFT

    67.3 GB

    VRAM

    —

    MTP

    54.9 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=24 running model_id=50 at Q8_0