Arao AI
Back to search results

gemma-4-12B-it · IQ3_XS

Start a discussion
AMD Radeon RX 907016GBvLLM v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ3_XS) on AMD Radeon RX 9070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

114.22 tok/s

Decode

Decode speed

439.54 tok/s

Prefill

Prefill speed

0.8 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

Today

Last verified

Performance

  1. vLLM · IQ3_XS (current)Decode 114.22 · Prefill 439.54 ·
  2. llama.cpp · IQ2_M Decode 86.99 · Prefill 431.57 ·

Core figures

Decode (avg)
114.22 tok/s
Prefill (avg)
439.54 tok/s
TTFT (avg)
0.8 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.91 GB
Power draw
200.9 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ3_XS
Framework
vLLM
Version
v0.36
Context length
8192 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 Radeon RX 9070
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
12.4
Power draw
200.9 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.36 · Ubuntu 24.04 · CUDA 12.4 · 8192 ctx

    114.22 tok/s

    Decode

    439.54 tok/s

    Prefill

    0.8 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    200.9 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=21 running model_id=65 at IQ3_XS