Arao AI
Back to search results

Ministral-3-8B-Instruct-2512 · Q2_K

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

This page aggregates 1 real-world runs of Ministral-3-8B-Instruct-2512 (Q2_K) on AMD Ryzen AI Max+ 395 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

42.14 tok/s

Decode

Decode speed

173.71 tok/s

Prefill

Prefill speed

2.26 s

TTFT

Time to first token

11.34 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

11 days ago

Last verified

Performance

  1. llama.cpp · Q2_K (current)Decode 42.14 · Prefill 173.71 ·
  2. Ollama · Q3_K_L Decode 32.47 · Prefill 141.58 ·

Core figures

Decode (avg)
42.14 tok/s
Prefill (avg)
173.71 tok/s
TTFT (avg)
2.26 s
VRAM (avg)
11.34 GB
MTP acceptance rate
—
TTFB
0.34 GB
Power draw
47.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Ministral-3-8B-Instruct-2512
Quantization
Q2_K
Framework
llama.cpp
Version
v0.27
Context length
65536 tokens
Batch size
256
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)
11.34 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.12
CUDA
12.8
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 2026-10-24

    v0.27 · Ubuntu 22.04 · CUDA 12.8 · 65536 ctx

    42.14 tok/s

    Decode

    173.71 tok/s

    Prefill

    2.26 s

    TTFT

    11.34 GB

    VRAM

    —

    MTP

    47.7 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=24 running model_id=74 at Q2_K