Arao AI
Back to search results

gemma-4-12B-it · IQ2_M

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBllama.cpp v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_M) on NVIDIA RTX 4060 Ti 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

81.49 tok/s

Decode

Decode speed

352.61 tok/s

Prefill

Prefill speed

1.33 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

5 days ago

Last verified

Performance

  1. vLLM · Q3_K_S Decode 104.24 · Prefill 463.62 ·
  2. llama.cpp · IQ2_M (current)Decode 81.49 · Prefill 352.61 ·
  3. Ollama · IQ1_S Decode 78.54 · Prefill 337.36 ·
  4. Ollama · Q2_K Decode 74.86 · Prefill 405.27 ·

Core figures

Decode (avg)
81.49 tok/s
Prefill (avg)
352.61 tok/s
TTFT (avg)
1.33 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.65 GB
Power draw
323.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ2_M
Framework
llama.cpp
Version
v0.41
Context length
32768 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
NVIDIA RTX 4060 Ti 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
15.2 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
12.4
Power draw
323.5 W

Sources & evidence

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

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

    v0.41 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx

    81.49 tok/s

    Decode

    352.61 tok/s

    Prefill

    1.33 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    323.5 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=3 running model_id=65 at IQ2_M