self-hosted/ai
§01·model · /models

falcon2 11b

llmactiveTII Falcon License 2.0

11B multilingual LLM by TII, the Falcon 2 generation. One recipe covers it here, on an 8 GB RTX 3060 Ti at 31.2 tokens/s in the shared 4-bit Ollama run — essentially level with the 7B first-generation Gemma on that same card, despite being half again as large. TII Falcon License 2.0, not a standard open licence.

§02·GPUs that run this model
1 total

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