self-hosted/ai
§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

benchmarked·~ runs via recipe (not benchmarked)· untested·doesn't fit