Arao AI
Back to search results

gemma-4-12B-it · Q5_K_S

Start a discussion
NVIDIA RTX 509032GBvLLM v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q5_K_S) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

173.67 tok/s

Decode

Decode speed

792.94 tok/s

Prefill

Prefill speed

2.27 s

TTFT

Time to first token

24.78 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ3_S Decode 261.31 · Prefill 1085.12 ·
  2. vLLM · Q5_K_S (current)Decode 173.67 · Prefill 792.94 ·
  3. Strata · Q3_K_M Decode 340.87 · Prefill 1525.66 ·
  4. llama.cpp · IQ2_XS Decode 253.43 · Prefill 894.02 ·
  5. llama.cpp · IQ3_S Decode 214.27 · Prefill 831.85 ·
  6. vLLM · IQ1_S Decode 298.32 · Prefill 1152.98 ·
  7. vLLM · IQ2_M Decode 288.51 · Prefill 940.03 ·
  8. Ollama · IQ2_XS Decode 246.6 · Prefill 1083.78 ·
  9. vLLM · Q8_0 Decode 117.2 · Prefill 879 ·
  10. vLLM · Q5_K_M Decode 171.1 · Prefill 1283.3 ·
  11. vLLM · Q4_K_M Decode 208.7 · Prefill 1565.3 ·
  12. llama.cpp · Q8_0 Decode 107.5 · Prefill 806.3 ·
  13. llama.cpp · Q5_K_M Decode 157.1 · Prefill 1178.3 ·
  14. llama.cpp · Q4_K_M Decode 191.5 · Prefill 1436.3 ·

Core figures

Decode (avg)
173.67 tok/s
Prefill (avg)
792.94 tok/s
TTFT (avg)
2.27 s
VRAM (avg)
24.78 GB
MTP acceptance rate
—
TTFB
1.39 GB
Power draw
467.4 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q5_K_S
Framework
vLLM
Version
v0.33
Context length
32768 tokens
Batch size
8
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
NVIDIA RTX 5090
Nominal VRAM
32 GB
Measured VRAM (avg)
24.78 GB
OS
Ubuntu 22.04
Driver
560.94
CUDA
13.0
Power draw
467.4 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

    v0.33 · Ubuntu 22.04 · CUDA 13.0 · 32768 ctx

    173.67 tok/s

    Decode

    792.94 tok/s

    Prefill

    2.27 s

    TTFT

    24.78 GB

    VRAM

    —

    MTP

    467.4 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=13 running model_id=65 at Q5_K_S