---
license: gemma
language:
- en
library_name: mlx
tags:
- applescript
- macos
- computer-use
- agent
- tool-calling
- function-calling
- mlx
- moe
- osaurus
base_model: google/gemma-4-26B-A4B-it
pipeline_tag: text-generation
---

![Osaurus](./osaurus-x-banner.png)

# AppleScript-16B-A4B-JANG_4M

**The flagship tool-calling model for macOS AppleScript & agentic computer-use.** Given a
`run_applescript` tool, it emits a structured **tool call** with correct AppleScript to drive macOS —
app automation (Safari, Finder, Mail, Notes, Calendar, Reminders, System Events), system control,
clipboard, screenshots, ASObjC, and `do shell script` — ready to execute in an agent loop. Without a
tools spec, it writes AppleScript directly (hybrid).

Built by **[Osaurus](https://osaurus.ai)**. Derived from **gemma-4-26B-A4B** (MoE): expert-pruned to a
hyper-focused **16.1 B** (~4 B active), fine-tuned for AppleScript + tool-calling, quantized to
**JANG_4M** (8-bit attention, 4-bit routed experts) for fast on-device inference via
[MLX](https://github.com/ml-explore/mlx).

| | |
|---|---|
| Parameters | 16.1 B total · ~4 B active (MoE) |
| Quant | JANG_4M — 8-bit attention, **4-bit routed experts** |
| Size | ~11 GB |
| Tool-calling | native (gemma tool-call format), `run_applescript` |
| Runtime | MLX (Apple Silicon) / Osaurus |

## Benchmark — base vs final (held-out executable AppleScript bench, 87 tasks)

*Tool-call emission* = emits a valid `run_applescript` call. *Compile* = valid AppleScript. *Exec* = it
runs and returns the correct result.

| | Tool-call emission | Compile | Exec |
|---|---|---|---|
| Base gemma-4-26B-A4B | ✗ (writes raw, no tool calls) | ~88% | unreliable |
| **AppleScript-16B-A4B-JANG_4M** | **100%** ⭐ | **100%** ⭐ | **84%** ⭐ |

Highest-quality AppleScript model in the Osaurus line: 100% structured tool-call emission, 100% valid
AppleScript, 84% executable correctness.

## Usage (MLX, tool-calling)

```python
from mlx_lm import load, generate
model, tok = load("OsaurusAI/AppleScript-16B-A4B-JANG_4M")
tools = [{"type":"function","function":{"name":"run_applescript",
  "description":"Execute AppleScript on macOS and return its output.",
  "parameters":{"type":"object","properties":{"script":{"type":"string"}},"required":["script"]}}}]
msgs = [{"role":"user","content":"Create a note titled 'Groceries' in Notes."}]
prompt = tok.apply_chat_template(msgs, tools=tools, add_generation_prompt=True, tokenize=False)
print(generate(model, tok, prompt=prompt, max_tokens=300))
```

Your agent parses the `run_applescript` tool call, runs the script (e.g. via `osascript`), and feeds
the result back. (Omit `tools=` to get raw AppleScript instead.)

## Tiers

- **AppleScript-16B-A4B-JANG_4M** (this) — flagship quality (~11 GB).
- **AppleScript-8B-JANG_4M** — fast/small tier (~5.6 GB).

## License

Inherits the **Gemma** license — review and comply with the base model's terms.

---
Made by Osaurus · contact **eric@osaurus.ai**