Arao AI
Back to search results

gemma-4-12B-it · Q2_K

Start a discussion
AMD Radeon RX 9070 XT16GBllama.cpp v0.55L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q2_K) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

126.21 tok/s

Decode

Decode speed

558.74 tok/s

Prefill

Prefill speed

2.24 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. llama.cpp · Q2_K (current)Decode 126.21 · Prefill 558.74 ·
  2. Strata · IQ3_XS Decode 157.74 · Prefill 536.72 ·
  3. Ollama · IQ2_XS Decode 93.98 · Prefill 376.98 ·

Core figures

Decode (avg)
126.21 tok/s
Prefill (avg)
558.74 tok/s
TTFT (avg)
2.24 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
1.01 GB
Power draw
231.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q2_K
Framework
llama.cpp
Version
v0.55
Context length
8192 tokens
Batch size
512
GPU layers
99
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 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.12
CUDA
12.6
Power draw
231.5 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

    v0.55 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx

    126.21 tok/s

    Decode

    558.74 tok/s

    Prefill

    2.24 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    231.5 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=16 running model_id=65 at Q2_K