Tuned Tensor

The closed-loop alternative to a raw tuning API

Tinker gives you a tuning API. Tuned Tensor gives you the whole closed loop — behaviour spec, fine-tune, evaluate, auto-tune — as an MIT-licensed CLI you run and inspect yourself.

npm i -g @tuned-tensor/cli
tt init
tt runs start <spec-id>

Open source CLI tool (MIT) on GitHub. Agent-readable workflow at /skill.md.

How it compares

Everything a raw tuning API leaves to you

Tinker hands you low-level training primitives and full control — you write the loop, the evals, and the iteration. Tuned Tensor is the opinionated layer on top: describe behaviour in a spec, and it compiles, augments, fine-tunes, evaluates, and auto-tunes for you, then hands you a small local model.

Tuned Tensor
Raw API
Describe behaviour in a structured specWrite a training loop
No training-loop or GPU code to write
AI-augments your examples into a training set
Built-in evaluation every run (LLM-as-judge)DIY (cookbook)
Regression detection across runsDIY
Auto-tune loop from evaluation feedback
One-command export to GGUF / OllamaDownload weights
Agent-readable workflow (/skill.md)
Full low-level control at research scale (1B–1T+)Small models (2–4B)
Managed training infrastructure

Both are managed services with open-source pieces: the Tuned Tensor CLI is MIT-licensed, and Tinker ships an open-source cookbook. The difference is the workflow — a behaviour spec and a built-in closed loop versus a low-level training API you build on.

A closed loop from behaviour spec to model

Tuned Tensor turns a behaviour spec into a tuned open-weight model, then uses regression reports to improve the next run.

01

Write the behaviour spec

Rules, constraints, examples, and target base model.

02

Fine-tune locally sized models

Compile training data and tune a small open-weight model.

03

Measure regressions

Score outputs, inspect failures, and compare against baselines.

04

Auto-tune loop

Use AI feedback to improve the spec and start the next run.

Each run preservesVersioned
Spec version
Run report
AI feedback
Next iteration

Auto-tune can repeat the loop until the target score is reached or the iteration limit is hit.

Use case story

Fine-tune a small model to triage email

We fine-tuned Qwen 3.5 2B on a public 10k-row dataset to triage email into a strict JSON object — triage action, priority, and prompt-injection risk — then measured the gains against the base model on held-out test examples.

Test pass rate

61.5%89.0%

Test avg score

0.5370.862

Dataset

10,000 rows

Want to learn more?

Explore the documentation to see how behaviour specs, runs, and evaluations work under the hood.