v0.1.7

magnitudedev/magnitudev0.1.7Jan 16, 2026by chonknick

Upgrading?

AI Summary

This release introduces support for Voyage 4 embedding models, offering various optimized sizes with extended context capabilities.

Key Highlights

  • Added Voyage 4 model variants (large, mid, lite, nano) with varying performance profiles
  • Support for 32,000 token context length across all models
  • Flexible dimensions via Matryoshka learning (2048/1024/512/256)
  • Multiple quantization formats including float, int8, and binary

New Features

  • Voyage 4 embedding integration
  • Matryoshka dimension support
  • Quantization support

Full Release Notes

## What's New

- Added support for Voyage 4 embedding models:
  - `voyage-4-large` - Flagship MoE model, #1 on MTEB (78.26)
  - `voyage-4` - Mid-sized balanced model
  - `voyage-4-lite` - Lightweight model, #9 on MTEB (73.29)
  - `voyage-4-nano` - Open-weight model (Apache 2.0)

All Voyage 4 models support:
- 32,000 token context
- Flexible dimensions (2048/1024/512/256) via Matryoshka learning
- Multiple quantization formats (float, int8, binary)

Related Repositories