# Distilling Desktop Automation into Sub-1B Models

> **Monograph 02** // Author: Asim Ansari (@asimibnakhlaque) // Date: September 2026 // Domain: SLM Distillation & Systems

Running 70-billion parameter models to query CPU metrics, manage background daemons, or launch local utilities is computationally absurd. By establishing orthogonal tool contracts and filtering synthetic action traces across 4 mechanical verification gates, we can distill deterministic desktop agency into Sub-1B models like SmolLM2-360M and Qwen2.5-0.5B.

---

## 1. The Latency and Memory Bottleneck

Autonomous desktop agents require tight interactive loops: parse natural language intent, invoke system tools, verify machine responses, and iterate. When powered by cloud-hosted frontier models, round-trip latency averages between 1,200ms and 4,500ms per action, introducing privacy hazards and recurring API expenses.

On local workstations, allocating 16GB–48GB of VRAM solely for basic shell and desktop operations restricts running concurrent developer workflows. The engineering goal of the NanoHat project was clear: **Can we distill OS tool calling into sub-1B parameter models that run on local CPU cores with sub-second latency and zero external framework overhead?**

---

## 2. Canonical Tool Contracts

Small language models (SLMs) fail when tool interfaces are ambiguous or verbose. To enable sub-1B models to generalize without hallucinations, we defined a strict, orthogonal set of machine-checkable tool primitives:

```typescript
// NanoHat Canonical OS Tool Contracts
type OSToolCall = 
  | { tool: "system_action", action: "launch_app" | "toggle_wifi" | "lock_screen" | "take_screenshot", target?: string }
  | { tool: "system_health", target: "cpu" | "ram" | "disk" | "network" | "battery" | "processes" }
  | { tool: "scheduler", action: "add" | "list" | "remove", task: string, due?: string }
  | { tool: "user_memory", action: "get" | "set" | "list", key: string, value?: string }
  | { tool: "calculator", expression: string }
  | { tool: "web_search", query: string };
```

Every tool response returns a machine-checkable string prefixed explicitly with `OK: [payload]` or `ERROR[reason]: [payload]`. Destructive operations (such as process killing or service restarts) enforce fail-closed TTY safety gates that reject unverified execution in headless environments.

---

## 3. The 4-Gate Mechanical Verification Pipeline

Training small models on unfiltered synthetic trajectories causes catastrophic drift—a single ungrounded hallucination in fine-tuning degrades the entire parameter subspace. To train on 250,600 multi-turn conversations (152.7M tokens), we passed every trace through 4 automated validation gates:

- **GATE 01 // SYNTAX & SCHEMA (Byte-Plausibility Verification):** Validates strict JSON syntax, tool delimiters, and verifies return payloads match `OK:` or `ERROR[reason]:` byte signatures.
- **GATE 02 // ENVIRONMENT REPLAY (Mock Backend Replay Grounding):** Re-executes tool calls against simulated Linux OS fixtures (Fedora systemd, D-Bus, sysfs) to verify actionable behavior.
- **GATE 03 // INFORMATION DENSITY (High-Entropy Word-Count Ceilings):** Enforces strict token entropy thresholds, stripping out conversational filler and repetitive boilerplate that dilutes weights.
- **GATE 04 // DATASET PURITY (Deduplication & Fingerprint Uniqueness):** Evaluates structural n-gram fingerprints across all 250,600 traces to eliminate dataset redundancy and prevent sample memorization.

---

## 4. Zero-Bloat Standard Library Runtime

Standard agent frameworks (LangChain, smolagents, LlamaIndex) drag along hundreds of megabytes of Python dependencies. In NanoHat, we eliminated third-party framework overhead entirely by building the harness with pure Python standard library modules: `asyncio`, `subprocess`, `urllib`, and `pathlib`.

| Benchmark Metric | Framework Agents (LangChain/smolagents) | NanoHat Native Stdlib |
| :--- | :--- | :--- |
| **Python Dependencies** | 45+ packages (Pydantic, Requests, etc.) | **0 external packages** |
| **Cold-Start Overhead** | 1,400 ms – 3,200 ms | **< 35 ms** |
| **Runtime RAM Footprint** | 450 MB – 1.8 GB | **< 48 MB** (excluding model) |
| **Local Inference Model** | Cloud API Dependent | **GGUF Quantized (Local CPU)** |

---

## 5. Results & Takeaways

Distilled over our verified 250,600 multi-turn dataset with response-only loss masking, **SmolLM2-360M** and **Qwen2.5-0.5B** achieved high completion accuracy across common OS diagnostic and workflow automation tasks.

Exported into quantized GGUF formats (`Q4_K_M`), these sub-1B models execute locally via Ollama and lightweight engines, proving that specialized, small models with clean tool contracts can replace bulky cloud architectures for desktop agency.