self-hosted/ai
§01·model · /models

gemma 7b

llmactiveGemma License

7B instruction-tuned LLM by Google (first-generation Gemma). Gemma License.

§02·GPUs that run this model
1 total
GPUVRAMSeriesBest speedMin VRAMWorksBenchmarksRecipe
RTX 3060 Ti8GB3031.95tokens/s8GB1recipecheck ↗

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