Arao AI
Back to search results

gemma-4-12B-it · IQ1_S

Start a discussion
AMD Radeon RX 7800 XT16GBvLLM v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ1_S) on AMD Radeon RX 7800 XT with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

105.74 tok/s

Decode

Decode speed

495.52 tok/s

Prefill

Prefill speed

0.97 s

TTFT

Time to first token

12.68 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 · IQ1_S (current)Decode 105.74 · Prefill 495.52 ·

Core figures

Decode (avg)
105.74 tok/s
Prefill (avg)
495.52 tok/s
TTFT (avg)
0.97 s
VRAM (avg)
12.68 GB
MTP acceptance rate
—
TTFB
0.85 GB
Power draw
252.2 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ1_S
Framework
vLLM
Version
v0.36
Context length
4096 tokens
Batch size
16
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 7800 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
12.68 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
252.2 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

    v0.36 · Ubuntu 24.04 · CUDA N/A · 4096 ctx

    105.74 tok/s

    Decode

    495.52 tok/s

    Prefill

    0.97 s

    TTFT

    12.68 GB

    VRAM

    —

    MTP

    252.2 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=31 running model_id=65 at IQ1_S