Arao AI
Back to search results

Raon-1-mini-preview · IQ2_M

Start a discussion
AMD Ryzen AI Max+ 395128GBllama.cpp v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Raon-1-mini-preview (IQ2_M) on AMD Ryzen AI Max+ 395 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

46.26 tok/s

Decode

Decode speed

241.55 tok/s

Prefill

Prefill speed

2.49 s

TTFT

Time to first token

33.55 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

14 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M (current)Decode 46.26 · Prefill 241.55 ·
  2. Ollama · IQ2_M Decode 44.23 · Prefill 204.06 ·

Core figures

Decode (avg)
46.26 tok/s
Prefill (avg)
241.55 tok/s
TTFT (avg)
2.49 s
VRAM (avg)
33.55 GB
MTP acceptance rate
—
TTFB
0.37 GB
Power draw
52.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Raon-1-mini-preview
Quantization
IQ2_M
Framework
llama.cpp
Version
v0.21
Context length
4096 tokens
Batch size
256
GPU layers
28
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)
33.55 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
12.4
Power draw
52.4 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-22

    v0.21 · Ubuntu 24.04 · CUDA 12.4 · 4096 ctx

    46.26 tok/s

    Decode

    241.55 tok/s

    Prefill

    2.49 s

    TTFT

    33.55 GB

    VRAM

    —

    MTP

    52.4 W

    Power draw

    L2 batch seed 2026-10-22: llama.cpp on hw_id=24 running model_id=93 at IQ2_M