gemma-4-12B-it · Q3_K_L
This page aggregates 1 real-world runs of gemma-4-12B-it (Q3_K_L) on NVIDIA RTX Spark with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
43.89 tok/s
Decode
Decode speed
217.76 tok/s
Prefill
Prefill speed
0.56 s
TTFT
Time to first token
20.24 GB
VRAM
VRAM usage
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- llama.cpp · Q3_K_L (current)Decode 43.89 · Prefill 217.76 ·
- llama.cpp · Q4_K_M Decode 39.59 · Prefill 158.74 ·
- Ollama · FP16 Decode 18.58 · Prefill 81.79 ·
- Ollama · Q4_K_M Decode 36.57 · Prefill 126.77 ·
Core figures
- Decode (avg)
- 43.89 tok/s
- Prefill (avg)
- 217.76 tok/s
- TTFT (avg)
- 0.56 s
- VRAM (avg)
- 20.24 GB
- MTP acceptance rate
- —
- TTFB
- 0.35 GB
- Power draw
- 68.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-12B-it
- Quantization
- Q3_K_L
- Framework
- llama.cpp
- Version
- v0.27
- Context length
- 4096 tokens
- Batch size
- 256
- GPU layers
- 20
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX Spark
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 20.24 GB
- OS
- Windows 11 24H2
- Driver
- NVIDIA 590.10
- CUDA
- 13.0
- Power draw
- 68.2 W
- Reference price
- $2,399 · updated 2026-10-19
Prices are not live; check the store page
Sources & evidence
1 measured records in total, each traceable to its original source
v0.27 · Windows 11 24H2 · CUDA 13.0 · 4096 ctx
43.89 tok/s
Decode
217.76 tok/s
Prefill
0.56 s
TTFT
20.24 GB
VRAM
—
MTP
68.2 W
Power draw
L2 batch seed 2026-10-19: llama.cpp on hw_id=110 running model_id=65 at Q3_K_L