Arao AI
Back to search results

gemma-4-12B-it · Q3_K_S

Start a discussion
NVIDIA RTX 509032GBOllama v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q3_K_S) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

236.13 tok/s

Decode

Decode speed

819.72 tok/s

Prefill

Prefill speed

1.31 s

TTFT

Time to first token

18.48 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS Decode 262.05 · Prefill 997.54 ·
  2. llama.cpp · Q8_0 Decode 125.52 · Prefill 751.15 ·
  3. Ollama · Q3_K_S (current)Decode 236.13 · Prefill 819.72 ·
  4. Ollama · Q5_K_S Decode 165.12 · Prefill 690.64 ·
  5. vLLM · IQ3_S Decode 261.31 · Prefill 1085.12 ·
  6. vLLM · Q5_K_S Decode 173.67 · Prefill 792.94 ·
  7. Strata · Q3_K_M Decode 340.87 · Prefill 1525.66 ·
  8. llama.cpp · IQ3_S Decode 214.27 · Prefill 831.85 ·
  9. vLLM · IQ1_S Decode 298.32 · Prefill 1152.98 ·
  10. vLLM · IQ2_M Decode 288.51 · Prefill 940.03 ·
  11. Ollama · IQ2_XS Decode 246.6 · Prefill 1083.78 ·
  12. vLLM · Q8_0 Decode 117.2 · Prefill 879 ·
  13. vLLM · Q5_K_M Decode 171.1 · Prefill 1283.3 ·
  14. vLLM · Q4_K_M Decode 208.7 · Prefill 1565.3 ·
  15. llama.cpp · Q5_K_M Decode 157.1 · Prefill 1178.3 ·
  16. llama.cpp · Q4_K_M Decode 191.5 · Prefill 1436.3 ·

Core figures

Decode (avg)
236.13 tok/s
Prefill (avg)
819.72 tok/s
TTFT (avg)
1.31 s
VRAM (avg)
18.48 GB
MTP acceptance rate
—
TTFB
1.89 GB
Power draw
363.9 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q3_K_S
Framework
Ollama
Version
v0.30
Context length
32768 tokens
Batch size
256
GPU layers
33
Flash Attention
Off

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)
18.48 GB
OS
Ubuntu 24.04
Driver
572.83
CUDA
12.8
Power draw
363.9 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.30 · Ubuntu 24.04 · CUDA 12.8 · 32768 ctx

    236.13 tok/s

    Decode

    819.72 tok/s

    Prefill

    1.31 s

    TTFT

    18.48 GB

    VRAM

    —

    MTP

    363.9 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=13 running model_id=65 at Q3_K_S