Arao AI
Back to search results

gemma-4-12B-it · IQ2_XS

Start a discussion
AMD Radeon RX 9070 XT16GBOllama v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_XS) on AMD Radeon RX 9070 XT with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

93.98 tok/s

Decode

Decode speed

376.98 tok/s

Prefill

Prefill speed

1.73 s

TTFT

Time to first token

14.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

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

Core figures

Decode (avg)
93.98 tok/s
Prefill (avg)
376.98 tok/s
TTFT (avg)
1.73 s
VRAM (avg)
14.2 GB
MTP acceptance rate
—
TTFB
0.75 GB
Power draw
294.9 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ2_XS
Framework
Ollama
Version
v0.51
Context length
8192 tokens
Batch size
512
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 Radeon RX 9070 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
14.2 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
294.9 W

Sources & evidence

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

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

    v0.51 · Ubuntu 22.04 · CUDA N/A · 8192 ctx

    93.98 tok/s

    Decode

    376.98 tok/s

    Prefill

    1.73 s

    TTFT

    14.2 GB

    VRAM

    —

    MTP

    294.9 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=16 running model_id=65 at IQ2_XS