Continuation Drafter
Choose a model for your machine
Model choice matters more than it looks, and memory is the first filter. Pick the card that matches your hardware.
Within about 3.3 points of the best closed-weight model measured, with nothing leaving the building. This is the strongest local option and it needs server hardware.
The best workstation-tier model measured. It failed the largest specification in the corpus (645 KB); for one that size, use gemma4:26b below, which drafted all ten.
Drafted every specification in the corpus, including the 645 KB one, and is honestly behind on drafting quality. Memory stays flat as the specification grows, which is what lets it finish the large ones.
Marginal, and uneven across specifications. Workable for trying the tool; treat its output as a rougher first pass than the tiers above.
Four commands and you are drafting
Install Ollama
Get it from ollama.com/download and start it. The desktop app starts the
server for you; otherwise run ollama serve.
Pull the model
A large download, once.
ollama pull gemma4:12bGet the binary
From the download page, then make it executable.
Draft
Point it at your specification and the filed parent claims.
DRAFT_MODEL=gemma4:12b ./continuation-drafter draft \
--spec spec.txt --parent parent-claims.txtOne caveat for this model
It did not complete the largest specification in the test corpus, about 645 KB. If yours is
that size, use gemma4:26b, which completed all ten, or halve the completion budget
with --max-tokens 8000 and retry.
Not enough memory, or would rather not install a model?
Run it through your own provider account instead. That sends the specification to that provider, so it suits published material, and for anything unpublished it is a judgment you make per matter. How that works.