Back to search results
gemma-4-12B-it · Q2_K
NVIDIA RTX 4060 Ti 16GB16GBOllama v0.20L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-12B-it (Q2_K) on NVIDIA RTX 4060 Ti 16GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
74.86 tok/s
Decode
Decode speed
405.27 tok/s
Prefill
Prefill speed
2.23 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
- vLLM · Q3_K_S Decode 104.24 · Prefill 463.62 ·
- llama.cpp · IQ2_M Decode 81.49 · Prefill 352.61 ·
- Ollama · IQ1_S Decode 78.54 · Prefill 337.36 ·
- Ollama · Q2_K (current)Decode 74.86 · Prefill 405.27 ·
Core figures
- Decode (avg)
- 74.86 tok/s
- Prefill (avg)
- 405.27 tok/s
- TTFT (avg)
- 2.23 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.6 GB
- Power draw
- 283 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- Q2_K
- Framework
- Ollama
- Version
- v0.20
- Context length
- 4096 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 4060 Ti 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 15.2 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.4
- Power draw
- 283 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.20 · Ubuntu 24.04 · CUDA 12.4 · 4096 ctx
74.86 tok/s
Decode
405.27 tok/s
Prefill
2.23 s
TTFT
15.2 GB
VRAM
—
MTP
283 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=3 running model_id=65 at Q2_K