Models

Two models. Two jobs.

Wowo7b for fast, everyday work. MochiBao32b for longer, more detailed work. Both free to run with Ollama, on your own machine.

Run them free

Free7B

Wowo7b

Turn a rough site note into a readable checklist, or a messy drawing note into a first draft you can edit. Based on Qwen2.5-7B-Instruct.

Size
4.7 GB
Speed, 32GB VRAM avg
169 tok/s

Use it for a first draft, then review it.

Free32B

MochiBao32b

For a full drawing quality note, a checklist with reasons, or a second pass over a long document. Based on Qwen3-32B.

Size
20 GB
Speed, 32GB VRAM avg
54 tok/s

Use it for longer work, then review it. Speeds are published 32GB VRAM averages.

Run them.

Ollama on your own machine. No account, no fee, no data sent to us. There is no public chat here.

# 7B
ollama pull qwen2.5:7b
ollama create wowo7b -f Modelfile.wowo7b

# 32B
ollama pull qwen3:32b
ollama create mochibao32b -f Modelfile.mochibao32b

Use them. Check them.

Use them for a first draft, a checklist, or a second pass over a document. Do not use them, unchecked, for a number on a drawing, an answer to a client, or any decision a licensed engineer has not reviewed.