← Home

It decided to download Ollama first (1.3GB)

NameTagSize
Qwen (fast)qwen3.5:4b3.4 GB
Qwen9qwen3.5:9b6.6 GB
Phi4phi4-mini2.5 GB
qwen3.5:2b~2.7 GB
granite4.2:3b~2 GB
gemma4:e2b~2–4 GB (tag-dependent)
qwen3.5:27b~17 GB
phi4 (14B)~9–12 GB

RAG, add nomic-embed-text at ~0.3 GB.

Can't LoRA on CPU. Expect hours to a couple of days on CPU, not minutes. But this is an add-on to the model that allows training.