Arao AI
Back to search results

Qwen3.5-27B · IQ3_S

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

This page aggregates 1 real-world runs of Qwen3.5-27B (IQ3_S) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

27.26 tok/s

Decode

Decode speed

100.74 tok/s

Prefill

Prefill speed

1.95 s

TTFT

Time to first token

39.52 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 Decode 18.22 · Prefill 78.36 ·
  2. Ollama · IQ3_S (current)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)
27.26 tok/s
Prefill (avg)
100.74 tok/s
TTFT (avg)
1.95 s
VRAM (avg)
39.52 GB
MTP acceptance rate
—
TTFB
0.22 GB
Power draw
56.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-27B
Quantization
IQ3_S
Framework
Ollama
Version
v0.22
Context length
4096 tokens
Batch size
512
GPU layers
99
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)
39.52 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
12.4
Power draw
56.5 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

    v0.22 · Windows 11 23H2 · CUDA 12.4 · 4096 ctx

    27.26 tok/s

    Decode

    100.74 tok/s

    Prefill

    1.95 s

    TTFT

    39.52 GB

    VRAM

    —

    MTP

    56.5 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=24 running model_id=50 at IQ3_S