Instructions to use OsaurusAI/AppleScript-8B-JANG_4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/AppleScript-8B-JANG_4M with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("OsaurusAI/AppleScript-8B-JANG_4M")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use OsaurusAI/AppleScript-8B-JANG_4M with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/AppleScript-8B-JANG_4M"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "OsaurusAI/AppleScript-8B-JANG_4M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OsaurusAI/AppleScript-8B-JANG_4M with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/AppleScript-8B-JANG_4M"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default OsaurusAI/AppleScript-8B-JANG_4M

Run Hermes

hermes

MLX LM

How to use OsaurusAI/AppleScript-8B-JANG_4M with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OsaurusAI/AppleScript-8B-JANG_4M"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OsaurusAI/AppleScript-8B-JANG_4M"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OsaurusAI/AppleScript-8B-JANG_4M",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

AppleScript-8B-JANG_4M

A fast, small 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, System Events), system control, clipboard, screenshots, and do shell script — ready to execute in an agent loop. Without a tools spec, it writes AppleScript directly (hybrid).

Built by Osaurus. Base: Zyphra/ZAYA1-8B (MoE). Quantized to JANG_4M (8-bit attention, 4-bit routed experts) for fast on-device inference via MLX.


Parameters	8.84 B (MoE)
Quant	JANG_4M — 8-bit attention, 4-bit routed experts
Size	~5.6 GB
Tool-calling	native (`<zyphra_tool_call>`), `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 = the script is valid AppleScript. Exec = it runs and returns the correct result (hardest pure-computational subset).

	Tool-call emission	Compile	Exec
Base (Zyphra/ZAYA1-8B)	✗ (writes raw, no tool calls)	28.9%	30.0%
AppleScript-8B-JANG_4M	100% ⭐	93.4% ⭐	70.8% ⭐

The fine-tune teaches reliable structured tool-calling and valid AppleScript (base does neither well). Exec is scored on the hardest computational subset; typical app-automation tool-calls land at the ~93% compile tier.

Usage (MLX, tool-calling)

from mlx_lm import load, generate
model, tok = load("OsaurusAI/AppleScript-8B-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":"Get the URL of the front Safari tab."}]
prompt = tok.apply_chat_template(msgs, tools=tools, add_generation_prompt=True, tokenize=False)
print(generate(model, tok, prompt=prompt, max_tokens=300))
# -> <zyphra_tool_call><function=run_applescript><parameter=script> ... </parameter>...

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

For higher accuracy use OsaurusAI/AppleScript-16B-A4B-JANG_4M (100% compile / 84% exec). This 8B is the fast/small tier for low-latency on-device automation.

License

Inherits the Zyphra/ZAYA1-8B license — review and comply with the base model's terms.

Made by Osaurus · contact eric@osaurus.ai

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized

Model tree for OsaurusAI/AppleScript-8B-JANG_4M

Base model

Zyphra/ZAYA1-base

Finetuned

Zyphra/ZAYA1-reasoning-base

Finetuned

Zyphra/ZAYA1-8B

Finetuned

(5)

this model