---
title: "Supported models"
description: "Which base models the Arkor backend accepts today, why the list is short, and where it's headed."
---

Today Studio's Playground (base-model mode) and Arkor's hosted inference serve exactly one base model: `gemma-4-E4B-it`. The `model` field of `createTrainer` itself accepts any model identifier the training backend can load; the starter templates target Gemma 4, which is also the base model hosted inference serves today. Below: what that value gets you and what's next.

## What you can pick today

`gemma-4-E4B-it` is the Gemma 4 instruction-tuned build, packaged by Unsloth for fast LoRA / QLoRA fine-tuning. Every starter template (`triage`, `translate`, `redaction`) targets it by default.

```ts
import { createTrainer } from "arkor";

export const trainer = createTrainer({
  name: "support-bot-v1",
  model: "unsloth/gemma-4-E4B-it",
  dataset: { type: "huggingface", name: "arkorlab/triage-demo" },
});
```

## What's coming

<CardGroup cols={2}>
  <Card title="Gemma 4 family" icon="layer-group" href="/docs/framework/roadmap#gemma-4-family">
    Open the `model` field to the full Gemma 4 family so you can pick the variant that matches your use case (size, capability, latency, quality).
  </Card>

  <Card title="Other open-weight families" icon="cubes" href="/docs/framework/roadmap#more-base-models">
    Expanding to additional open-weight families is on the Roadmap backlog.
  </Card>
</CardGroup>

## See also

- [Trainer concept](/docs/framework/concepts/trainer) for what the `model` field is and where it sits among the other fields.
- [`createTrainer` reference](/docs/framework/sdk/create-trainer) for the full `TrainerInput` type.
- [Roadmap](/docs/framework/roadmap) for the broader picture of what's next.