http://blogoxeokthu4ntl7tptzpjfjmlfxdzsff2ueviwj4vjf7z3aadnz2id.onion/opsec/openwebuilocalllms/index.html
Here're some of my picks for best self-hostable models currently available on ollama: - Gemma 3 Phi4 Granite 3.2* Qwen 2.5 llama 3.1 Trained by Google Microsoft IBM Alibaba Meta Released on 03-2025 12-2024 02-2025 09-2024 07-2024 Parameter count 12B 14B 8B 14B 8B Size (Q4_K_M) 8.1 GB 9.1 GB 4.9 GB 9.0 GB 4.9 GB Other variants 1B, 4B, 27B Phi4-mini 4B Vision 2B, 2B 0.5B, 1.5B, 3B, 7B, 32B, 72B, Qwen-coder 70B, 405B Good at Reasoning, explaining concepts, light programming, vision,...