A 4B model on my computer drafts freelance quotes. I tested it on 8 real client briefs.

Description and use

A local 4B model drafts freelance quotes by extracting scope from client briefs with Gemma via Ollama and estimating hours and price with TabPFN, keeping data private and eliminating guesswork.

Problem

Freelancers often guess hours for vague client briefs and discover the guess is wrong weeks later.

Outcome

On 8 real client briefs, briefquote returned valid output every time; 3 were usable as a first draft without major edits.

Workflow

• Paste client brief into briefquote UI
• Gemma 4B extracts structured scope JSON
• TabPFN estimates hours, price and on‑time probability from scope and past job data
• briefquote renders a Markdown quote draft
• Freelancer reviews and sends quote

Evidence

briefquote uses an open‑weight Gemma via Ollama to extract a structured scope from a client brief and TabPFN to estimate hours, price and on‑time probability, all without sending data to a third‑party API.

Source

On 8 real client briefs it returned valid output every time, and 3 were usable as a first draft without major edits.

Source

Gemma (gemma3:4b, running locally through Ollama) reads the messy prose and extracts a structured scope: project type, deliverables, integrations, a 1 to 5 complexity rating, plus the questions to ask the client and the risks to price in.

Source