Skip to main content
“og:title”: “Stenox Docs”
This is an AI ENHANCEMENT provider. It improves transcribed text with grammar correction and formatting. For speech-to-text transcription, see Transcription Providers.

​
Overview

MLX is Apple’s machine learning framework optimized for Apple Silicon. Stenox uses MLX to run small, efficient language models locally on your Mac for completely private text enhancement. Key Benefits:
  • 🔒 100% Private - Text never leaves your Mac
  • 🌐 Offline - Works without internet connection
  • 💰 Free - No API keys, no usage costs
  • 🚀 Optimized - Built for Apple Silicon

​
Privacy & Security

MLX processes everything locally on your Mac:
  • Transcribed text is enhanced on-device
  • No data sent to cloud services
  • No internet connection required
  • No API keys or accounts needed
  • Perfect for sensitive or confidential content
Combine MLX with WhisperKit (local transcription) for 100% private, offline voice dictation.

​
No API Key Required

Unlike cloud providers, MLX requires no setup:
  1. Select MLX in Stenox Settings
  2. Download your preferred model
  3. Start enhancing immediately
No registration, no API keys, no authentication.

​
Available Models

MLX offers several small language models optimized for Apple Silicon:
ModelSizeSpeedQualityRecommended For
Qwen 2.5 1.5B~1 GBFastestGoodQuick enhancement, limited RAM
Gemma 3n 2B~1.2 GBFastExcellentBest accuracy, recommended
Phi-3 Mini~2.4 GBMediumVery GoodBalanced quality and speed
Gemma 3n 4B~2.5 GBSlowerVery GoodHigher quality, more RAM
Qwen 3 4B~2.5 GBSlowerGoodAlternative to Gemma 3n 4B
Recommended for beginners: Gemma 3n 2B - Best accuracy with fast processing and reasonable size.

​
Model Selection Guide

Best for:
  • Quick enhancement (2-3 seconds)
  • 8GB RAM Macs
  • Everyday grammar correction
  • Speed over maximum quality
Processing time: ~2-3 seconds per paragraphQuality: Good grammar correction, basic formatting
Best for:
  • Higher quality enhancement
  • 12GB+ RAM Macs
  • More complex edits
  • Good balance of speed and quality
Processing time: ~3-4 seconds per paragraphQuality: Very good grammar, reliable formatting
Best for:
  • Maximum local quality
  • 16GB+ RAM Macs
  • Critical writing
  • Quality over speed
Processing time: ~4-6 seconds per paragraphQuality: Near-cloud quality, excellent at complex edits

​
Setup Instructions

1

Open Stenox Settings

Click the Stenox icon in your menu bar and select Settings.
2

Navigate to Models tab

Go to the Models tab in the Settings window.
3

Select MLX

Under AI Enhancement Provider, select MLX from the dropdown.
4

Choose a model

Select your preferred model:
  • Gemma 3n 2B (recommended - best accuracy)
  • Qwen 2.5 1.5B (fastest, smallest)
  • Phi-3 Mini (balanced quality)
  • Gemma 3n 4B or Qwen 3 4B (maximum quality)
5

Download the model

Click Download and wait for the model to download.Download sizes:
  • Qwen 2.5 1.5B: ~1 GB
  • Gemma 3n 2B: ~1.2 GB
  • Phi-3 Mini: ~2.4 GB
  • Gemma 3n 4B / Qwen 3 4B: ~2.5 GB
Models are stored in ~/stenox-models/mlx/ by default.
6

Start enhancing

Once download completes, your transcriptions will automatically be enhanced!

​
Performance

MLX performance depends on your Mac’s hardware and chosen model:

​
Apple Silicon Macs

Excellent performance:
  • Qwen 1.5B: 2-3 seconds per paragraph
  • Gemma 2B: 3-4 seconds per paragraph
  • Phi-3 3.8B: 5-7 seconds per paragraph
Optimized with:
  • Metal GPU acceleration
  • Apple Neural Engine (ANE)
  • Unified memory architecture

​
Intel Macs

Not supported:
  • MLX requires Apple Silicon
  • Intel Mac users should use cloud providers (Gemini or Groq)
MLX models only work on Apple Silicon Macs. Intel Mac users must use cloud enhancement providers.

​
Apple Silicon Required

MLX models require Apple Silicon (M1/M2/M3/M4). Intel Mac users should use cloud providers like Gemini or Groq.

​
What MLX Enhancement Does

​
Grammar Correction

  • Fixes grammatical errors
  • Subject-verb agreement
  • Tense corrections
  • Article usage (a, an, the)
Example:
  • Before: “me and sarah was going to store”
  • After: “Sarah and I were going to the store.”

​
Capitalization

  • Sentence beginnings
  • Proper nouns (names, places)
  • Acronyms and abbreviations
Example:
  • Before: “john lives in new york city and works for ibm”
  • After: “John lives in New York City and works for IBM.”

​
Punctuation

  • Adds missing commas, periods
  • Fixes run-on sentences
  • Improves readability
Example:
  • Before: “hello how are you doing today its nice to meet you”
  • After: “Hello, how are you doing today? It’s nice to meet you.”

​
Light Formatting

  • Number formatting (spelled out → digits)
  • Date and time formatting
  • Basic list formatting
MLX models provide basic to good enhancement. For maximum quality, consider cloud providers like Google Gemini.

​
When to Use MLX

Privacy is critical

Healthcare, legal, financial, or sensitive content.

Working offline

Airplanes, remote locations, or unreliable internet.

No API costs

No per-use charges. Processing happens on your Mac.

100% local setup

Combine with WhisperKit for completely offline dictation.

​
When to Use Cloud Instead

Consider cloud providers if you need:
  • Faster processing - Cloud is 2-3x faster (< 1 second vs 2-5 seconds)
  • Better quality - Gemini 2.5 Flash and Groq LLMs often outperform small MLX models
  • Intel Mac - MLX requires Apple Silicon
  • Complex edits - Tone adjustment, style changes, formatting
Use both! Create different Profiles:
  • MLX for personal notes (privacy)
  • Gemini for work emails (quality)
  • Auto-switch based on application

​
Custom Prompts

Configure how MLX enhances your text in Profile settings: 
Fix grammar and punctuation errors.
Keep the original meaning and tone.

​
Troubleshooting

  • Check internet connection
  • Ensure sufficient disk space (~2-4 GB per model)
  • Try downloading again
  • Check ~/stenox-models/mlx/ for partial downloads and delete them
  • Try a smaller model (Qwen 2.5 1.5B or Gemma 3n 2B instead of larger models)
  • Close other intensive applications
  • Check Activity Monitor for available RAM
  • Your Mac may not have enough RAM for larger models
  • Try Gemma 3n 2B (best accuracy) or a larger model
  • Adjust custom prompt in Profile settings
  • For maximum quality, use cloud providers (Gemini)
  • Add specific formatting instructions to your custom prompt
  • Your model is too large for available RAM
  • Use Qwen 2.5 1.5B or Gemma 3n 2B on 8GB Macs
  • Upgrade to 16GB+ RAM for larger models
  • Close other applications to free memory

​
Model Comparison

ModelRAM RequiredSpeedQualityBest Use Case
Qwen 2.5 1.5B8GB+FastestGoodQuick tasks, 8GB Macs
Gemma 3n 2B8GB+FastExcellentRecommended for most users
Phi-3 Mini12GB+MediumVery GoodBalanced quality and speed
Gemma 3n 4B16GB+SlowerVery GoodHigher quality, 16GB Macs
Qwen 3 4B16GB+SlowerGoodAlternative larger model

​
Next Steps

WhisperKit (Local)

Combine with WhisperKit for 100% private, offline dictation.

Create Profiles

Different providers for different scenarios.

Privacy-First Setup

Complete guide to local-only Stenox configuration.

Cloud Enhancement

Try cloud enhancement for comparison.
Perfect for privacy: MLX + WhisperKit = No cloud providers, no API keys, no internet required, complete privacy.