Arao AI
Back to search results

gemma-4-12B-it · IQ2_M

Start a discussion
AMD Radeon AI PRO R970032GBvLLM v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_M) on AMD Radeon AI PRO R9700 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

125.41 tok/s

Decode

Decode speed

606.9 tok/s

Prefill

Prefill speed

0.12 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · IQ2_M (current)Decode 125.41 · Prefill 606.9 ·

Core figures

Decode (avg)
125.41 tok/s
Prefill (avg)
606.9 tok/s
TTFT (avg)
0.12 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
1 GB
Power draw
274.4 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ2_M
Framework
vLLM
Version
v0.32
Context length
32768 tokens
Batch size
16
GPU layers
999
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
AMD Radeon AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
274.4 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.32 · Ubuntu 22.04 · CUDA N/A · 32768 ctx

    125.41 tok/s

    Decode

    606.9 tok/s

    Prefill

    0.12 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    274.4 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=79 running model_id=65 at IQ2_M