# Jeff — Jev-compatible 0.8B decision models trained on one home GPU

> Three tiny open models that pick between options you describe in plain words, in about 22 milliseconds.

- Org: Firelex
- Date: 2026-09-28
- Category: model, repo, tool
- Source: https://github.com/firelex/jeff
- Canonical page: https://ai-tldr.dev/releases/firelex-jeff/

## In short

Jeff is a set of three small open decision models fine-tuned from Qwen3.5 and Gemma 4. They take Jev's request format and return a probability per option in about 22 ms. The 2B scores 83.1% across five benchmarks against Jev's published 83.0%.

## What it is

Jeff is a family of three zero-shot decision models — a 0.8B and a 2B fine-tune of Qwen3.5 and a fine-tune of Gemma 4 E2B — that accept the same request format as TypeSafe's Jev. You describe a situation and list the options in words, and Jeff returns a calibrated probability for each one. The project is independent and says it is not affiliated with or endorsed by TypeSafe.

## How it works

No text is generated: one forward pass reads a trained answer over the option letters, and a single fitted temperature calibrates the probabilities. The training code starts from Denis Yarats's open AutoJev recipe and adds small student models, a local synthetic-data pipeline with a leak filter, and MLX serving on Apple silicon. All synthetic data was written by the open Qwen3.8-Flash-Next on two DGX Sparks, and training ran on a single RTX PRO 6000 workstation GPU.

## Why it matters

Routing, moderation and intent calls can run locally in 22–60 ms instead of costing an API call each. The README is clear about the trade-off: Jeff wins on classification and grounding tests such as Financial PhraseBank (96.4%) but stays well below Jev on reasoning-heavy BBH and JudgeBench. A short fine-tune closes much of the gap for a narrow task — a voice-navigation run moved held-out accuracy from 31.7% to 95.8% in under half an hour.

## Who it's for

backend and agent engineers who need fast local classification

## Try it

uv run hf download mstrasser/Jeff-Qwen3.5-0.8B --local-dir checkpoints/jeff-0.8b

## Quick facts

- Maker: Firelex (independent, not affiliated with TypeSafe)
- Models: Jeff-Qwen3.5-0.8B, Jeff-Qwen3.5-2B, Jeff-Gemma4-E2B
- License: Code MIT, weights Apache 2.0
- Question types: choice (up to 255 options), noul, score
- Training: One RTX PRO 6000; 0.8B in ~2 h, 2B in ~3.5 h
- Runs on: NVIDIA GPU, CPU, Apple silicon (MLX, Qwen only)

## FAQ

### Is Jeff made by TypeSafe, the company behind Jev?

No. Jeff uses the same request format as Jev, so code written for Jev can talk to a local Jeff server, but the README states the project is not affiliated with or endorsed by TypeSafe. Jeff's training code started as a fork of Denis Yarats's open-source AutoJev recipe, which is MIT-licensed.

### Which Jeff model should I pick, 0.8B or 2B?

For fast option picking the Jeff README recommends the 0.8B. The 2B scores higher on benchmarks (83.1% overall against 79.1%) but the authors found it more cautious and a weaker game player, collecting 41.2 Pac-Man pellets against the 0.8B's 57.0. The 0.8B also runs at 28 ms on an M4 Max against 60 ms for the 2B.

### Can Jeff replace a large model for reasoning tasks?

No. The Jeff authors say small models don't reason: expect fast, calibrated choices between options you describe, not multi-step reasoning. On BBH Jeff-Qwen3.5-2B scores 68.0% against Jev's published 94.3%, and on JudgeBench 64.6% against 78.6%. Jeff also handles English text only, and it cannot forecast — describe what each option leads to instead.

### Can I fine-tune Jeff on my own data?

Yes. Jeff's weights are Apache 2.0 and the repository includes the AutoJev-based training scripts. The authors fine-tuned it on about 11,000 voice-navigation examples in roughly half an hour on one GPU, moving held-out accuracy from 31.7% to 95.8% at about 40 ms per decision on an M4 Max.

## Links

- [GitHub Repo](https://github.com/firelex/jeff)
- [Model: Jeff 0.8B](https://huggingface.co/mstrasser/Jeff-Qwen3.5-0.8B)
- [Model: Jeff 2B](https://huggingface.co/mstrasser/Jeff-Qwen3.5-2B)
- [HN Discussion](https://news.ycombinator.com/item?id=49883844)
- [AutoJev Recipe](https://github.com/denis-pplx/autojev)