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. 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.
| 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)
from mlx_lm import load, generate
model, tok = load("JANGQ-AI/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