Skip to content

v3.6.0 - Initial LLM support, Supertonic v3

Choose a tag to compare

View all tags
@saddam213 saddam213 released this 23 Jul 00:42
· 16 commits to master since this release
v3.6.0
26295af
This commit was signed with the committer’s verified signature.
saddam213 Adam Clark
SSH Key Fingerprint: ewnBEXHp8fJq0n2RzK4DNknXtretrEoJPuCfp7CV5YE
Verified
Learn about vigilant mode.

Amuse v3.6.0 - Initial LLM support, Supertonic v3

We're excited to announce Amuse v3.6.0, bringing support for the latest AI models and introducing the first stage of integrated LLM capabilities.

✨ What's New

Supertonic v3 Support

Amuse now supports Supertonic v3, enabling compatibility with the latest version and its improvements.

Initial LLM Support

This release introduces the first phase of built-in Large Language Model (LLM) support, including:

  • Qwen 4B
  • Qwen 4B VL
  • Qwen 8B
  • Qwen 8B VL

The following AI processes are now available:

  • ImageToText – Generate text descriptions and analyze images.
  • Instruct – Execute instruction-following tasks using supported LLMs.

Looking Ahead

This is the foundation of Amuse's LLM integration. The next release will expand support with:

  • Larger language models
  • Interactive chat capabilities
  • Additional AI workflows and functions
  • Further performance and usability improvements

Stay tuned for even more powerful AI features in the next update.

2026-07-22.08-53-42.mp4

Installation

Upgrade from v3.2.0 - v3.5.8 is supported

1. Installer Version

Best for a standard Windows setup with automatic shortcuts.

  • New Install & Upgrade:
    1. Download and run Amuse_vX.X.X.exe.
    2. Follow the on-screen instructions.

2. Standalone Version

Best for custom drive locations.

New Install:

  1. Download and extract Amuse_vX.X.X.zip to your preferred folder.
  2. Run Amuse.exe.

Upgrade:

  1. Download and extract Amuse_vX.X.X.zip to a temp folder.
  2. Copy and overwrite all files in your existing location
  3. Run Amuse.exe.

Note: A fast SSD with plenty of free space is highly recommended, as model downloads can be large.
Note: Windows 11 users may need to Run As Administrator during environment creation if there are failures.

Device Compatibility

This new engine leverages a python based compute backend. Please note the following hardware requirements for this dev release:

  • NVIDIA: Supports all CUDA compatible devices (CUDA 13.0).

Full Changelog: v3.5.8...v3.6.0
GitHub Downloads (all assets, specific tag)

Assets 4
Loading