Arao AI
Back to search results

gemma-4-12B-it · Q3_K_S

Start a discussion
NVIDIA RTX 408016GBOllama v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q3_K_S) on NVIDIA RTX 4080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

117.06 tok/s

Decode

Decode speed

479.42 tok/s

Prefill

Prefill speed

0.34 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. Ollama · Q3_K_S (current)Decode 117.06 · Prefill 479.42 ·
  2. Strata · IQ1_S Decode 247.32 · Prefill 1242.06 ·

Core figures

Decode (avg)
117.06 tok/s
Prefill (avg)
479.42 tok/s
TTFT (avg)
0.34 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.94 GB
Power draw
285.6 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q3_K_S
Framework
Ollama
Version
v0.40
Context length
8192 tokens
Batch size
256
GPU layers
20
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4080
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
12.6
Power draw
285.6 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

    v0.40 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx

    117.06 tok/s

    Decode

    479.42 tok/s

    Prefill

    0.34 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    285.6 W

    Power draw

    L2 batch seed 2026-10-18: Ollama on hw_id=41 running model_id=65 at Q3_K_S