§01·model · /models
Gemma 2 9B
llmactiveGemma License
9B instruction-tuned LLM by Google — the Gemma 2 generation, well regarded for quality per parameter in its day. One recipe covers it, on an 8 GB RTX 3060 Ti at 23.8 tokens/s in the shared 4-bit Ollama run. The Gemma 4 entries in this catalogue reach far more hardware: the E4B variant covers all 27 cards. Gemma License.
§02·GPUs that run this model
1 total| GPU | VRAM | Series | Best speed | Min VRAM | Works | Evidence | |
|---|---|---|---|---|---|---|---|
| RTX 3060 Ti | 8GB | 30 | 23.8tokens/s | 8GB | ✓ | 1benchrecipe | check ↗ |
✓ benchmarked·~ runs via recipe (not benchmarked)·— untested·✕doesn't fit