Gemma 2 9B
by Google · gemma-2 family
9B
parameters
text-generation code-generation reasoning multilingual summarization
Gemma 2 9B is Google's mid-range open model that punches well above its weight, outperforming many larger models on key benchmarks. It incorporates knowledge distillation from larger Gemma models, resulting in exceptional quality for its parameter count. The model excels at reasoning, text generation, and multilingual tasks. With its 8K context window and moderate resource requirements, it is an excellent choice for users seeking strong general-purpose performance on consumer-grade hardware.
Quick Start with Ollama
ollama run 9b-instruct-q8_0 | Creator | |
| Parameters | 9B |
| Architecture | transformer-decoder |
| Context Length | 8K tokens |
| License | Gemma Terms of Use |
| Released | Jun 27, 2024 |
| Ollama | gemma2 |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M | 4.4 GB | 6.9 GB |
★
★
★
★
★
| 9b-instruct-q4_K_M |
| Q8_0 recommended | 8.1 GB | 11 GB |
★
★
★
★
★
| 9b-instruct-q8_0 |
| F16 | 17.1 GB | 20 GB |
★
★
★
★
★
| 9b-instruct-fp16 |
Compatible Hardware for Q8_0
Showing compatibility for the recommended quantization (Q8_0, 11 GB VRAM).
Compatible Hardware
Benchmark Scores
71.3
mmlu