Arao AI
Back to search results

gemma-4-12B-it · IQ2_XS

Start a discussion
NVIDIA RTX 509032GBllama.cpp v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_XS) on NVIDIA RTX 5090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

253.43 tok/s

Decode

Decode speed

894.02 tok/s

Prefill

Prefill speed

2.21 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

Today

Last verified

Performance

  1. llama.cpp · IQ2_XS (current)Decode 253.43 · Prefill 894.02 ·
  2. llama.cpp · IQ3_S Decode 214.27 · Prefill 831.85 ·
  3. vLLM · IQ1_S Decode 298.32 · Prefill 1152.98 ·
  4. vLLM · IQ2_M Decode 288.51 · Prefill 940.03 ·
  5. Ollama · IQ2_XS Decode 246.6 · Prefill 1083.78 ·
  6. vLLM · Q8_0 Decode 117.2 · Prefill 879 ·
  7. vLLM · Q5_K_M Decode 171.1 · Prefill 1283.3 ·
  8. vLLM · Q4_K_M Decode 208.7 · Prefill 1565.3 ·
  9. llama.cpp · Q8_0 Decode 107.5 · Prefill 806.3 ·
  10. llama.cpp · Q5_K_M Decode 157.1 · Prefill 1178.3 ·
  11. llama.cpp · Q4_K_M Decode 191.5 · Prefill 1436.3 ·

Core figures

Decode (avg)
253.43 tok/s
Prefill (avg)
894.02 tok/s
TTFT (avg)
2.21 s
VRAM (avg)
14.2 GB
MTP acceptance rate
—
TTFB
2.03 GB
Power draw
519.7 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.48
Context length
16384 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
14.2 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.8
Power draw
519.7 W

Sources & evidence

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

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

    v0.48 · Ubuntu 22.04 · CUDA 12.8 · 16384 ctx

    253.43 tok/s

    Decode

    894.02 tok/s

    Prefill

    2.21 s

    TTFT

    14.2 GB

    VRAM

    —

    MTP

    519.7 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=13 running model_id=65 at IQ2_XS