Gemma 2 9B
GoogleGoogle's mid-range model offering strong performance across tasks. Uses knowledge distillation techniques for quality that punches above its weight class.
Parameters 9B
Min VRAM 7 GB
Recommended VRAM 12 GB
Context Length 8K
License Gemma
🚀 Get Started
Run Gemma 2 9B locally with one command:
ollama run gemma2:9b Requires Ollama installed.
📊 Benchmarks
BenchmarkScore
MMLU 71.3
GSM8K 68.2
HumanEval 54.3
💻 Hardware Recommendations
🟢 Minimum
7 GB VRAM GPU or 14+ GB RAM (CPU mode)
Expect slower generation in CPU mode
🔵 Recommended
12 GB VRAM GPU
Fast generation with room for context