Back to search results
gemma-4-12B-it · Q3_K_S
NVIDIA RTX 4080 Super16GBOllama v0.29L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-12B-it (Q3_K_S) on NVIDIA RTX 4080 Super with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
129.2 tok/s
Decode
Decode speed
551.46 tok/s
Prefill
Prefill speed
0.82 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
- Ollama · Q3_K_S (current)Decode 129.2 · Prefill 551.46 ·
Core figures
- Decode (avg)
- 129.2 tok/s
- Prefill (avg)
- 551.46 tok/s
- TTFT (avg)
- 0.82 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 1.03 GB
- Power draw
- 236.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- Q3_K_S
- Framework
- Ollama
- Version
- v0.29
- Context length
- 4096 tokens
- Batch size
- 512
- 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 4080 Super
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 15.2 GB
- OS
- Ubuntu 22.04
- Driver
- 572.83
- CUDA
- 13.0
- Power draw
- 236.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.29 · Ubuntu 22.04 · CUDA 13.0 · 4096 ctx
129.2 tok/s
Decode
551.46 tok/s
Prefill
0.82 s
TTFT
15.2 GB
VRAM
—
MTP
236.5 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=20 running model_id=65 at Q3_K_S