Arao AI
Back to search results

Qwen3-4B · IQ2_M

Start a discussion
AMD Ryzen AI Max+ 395128GBOllama v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (IQ2_M) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

170.8 tok/s

Decode

Decode speed

683.91 tok/s

Prefill

Prefill speed

2.12 s

TTFT

Time to first token

6.47 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · Q6_K Decode 104.54 · Prefill 394.29 ·
  2. Ollama · IQ1_S Decode 170.91 · Prefill 585.17 ·
  3. Ollama · IQ2_M (current)Decode 170.8 · Prefill 683.91 ·
  4. Ollama · Q2_K Decode 165.94 · Prefill 894.2 ·
  5. Ollama · Q5_K_S Decode 109.99 · Prefill 499.66 ·

Core figures

Decode (avg)
170.8 tok/s
Prefill (avg)
683.91 tok/s
TTFT (avg)
2.12 s
VRAM (avg)
6.47 GB
MTP acceptance rate
—
TTFB
1.37 GB
Power draw
107.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
IQ2_M
Framework
Ollama
Version
v0.27
Context length
4096 tokens
Batch size
512
GPU layers
33
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)
6.47 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
N/A
Power draw
107.1 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

    v0.27 · Windows 11 23H2 · CUDA N/A · 4096 ctx

    170.8 tok/s

    Decode

    683.91 tok/s

    Prefill

    2.12 s

    TTFT

    6.47 GB

    VRAM

    —

    MTP

    107.1 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=24 running model_id=54 at IQ2_M