Arao AI
Back to search results

Qwen3.5-4B · IQ2_M

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.53L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (IQ2_M) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

61.41 tok/s

Decode

Decode speed

198.56 tok/s

Prefill

Prefill speed

0.4 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

17 days ago

Last verified

Performance

  1. vLLM · IQ2_M (current)Decode 61.41 · Prefill 198.56 ·
  2. Ollama · FP16 Decode 19.79 · Prefill 92.05 ·
  3. llama.cpp · IQ3_XS Decode 156.15 · Prefill 562.48 ·
  4. vLLM · IQ2_XS Decode 205.56 · Prefill 924.99 ·
  5. vLLM · Q6_K Decode 110.75 · Prefill 500.4 ·

Core figures

Decode (avg)
61.41 tok/s
Prefill (avg)
198.56 tok/s
TTFT (avg)
0.4 s
VRAM (avg)
6.47 GB
MTP acceptance rate
—
TTFB
0.49 GB
Power draw
47.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
IQ2_M
Framework
vLLM
Version
v0.53
Context length
4096 tokens
Batch size
8
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)
6.47 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
12.4
Power draw
47.7 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

    v0.53 · Windows 11 23H2 · CUDA 12.4 · 4096 ctx

    61.41 tok/s

    Decode

    198.56 tok/s

    Prefill

    0.4 s

    TTFT

    6.47 GB

    VRAM

    —

    MTP

    47.7 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=24 running model_id=48 at IQ2_M