# Smaug-Decisions audio, image and text models

> Smaug-Decisions is Abacus.AI's open 4B model for audio, images and text. Its family includes a 0.7B audio tier and a LiteRT build for phones.

Updated 2026-11-04 (Australia/Adelaide)

By Abacus.AI · Maker blog announcement: 2026-11-02 · OPEN

Abacus.AI's 4B decision model answers a typed question about audio, an image or text with a probability per option in one pass. It is a Gemma 4 E4B-it fine-tune. The family includes a 744M audio model and a LiteRT build for phones. Each 4B request takes one audio clip up to 30 seconds or one image, with up to 20 options.

## Facts

- Size: 4B effective, 8.6B stored; 744M audio tier
- Base: google/gemma-4-E4B-it; google/embeddinggemma-2 for the audio tier
- Licence: Apache-2.0
- Inputs: Audio, images and text; 2 to 20 options
- Formats: Transformers; LiteRT-LM; Core ML int8 for the audio tier

## Claims and sources

- **VENDOR-REPORTED**: On Abacus.AI's 6,671-item Earshot benchmark, the 4B scores 60.1 audio skill with ECE 0.069. Gemini 4 Argon scores 59.4 with ECE 0.123, and Gemini 3.8 Flash 50.5 with ECE 0.204. The 0.7B audio tier scores 53.0 with ECE 0.086. [source](<https://huggingface.co/abacusai/Smaug-Decisions>)
- **VENDOR-REPORTED**: Using the 0.7B audio tier first and escalating below 0.9 matches the 4B's 60.1 audio skill at 130 ms mean latency instead of 210 ms in Abacus.AI's run. [source](<https://huggingface.co/abacusai/Smaug-Audio-Decisions-0.7B>)
- **VENDOR-REPORTED**: Abacus.AI reports 57.9 on public Decision Index images and 56.6 on text. These are its own runs, not leaderboard submissions. [source](<https://huggingface.co/abacusai/Smaug-Decisions>)
- **VENDOR-REPORTED**: The 3.45 GB LiteRT build scores 59.4 audio skill in a PyTorch replica of its quantized weights. Abacus.AI measures about 0.6 seconds per text decision on an iPhone 14 Pro Max. [source](<https://huggingface.co/abacusai/Smaug-Decisions-LiteRT>)

## Links

- [Source: Weights and model card](<https://huggingface.co/abacusai/Smaug-Decisions>)
- [Source: 0.7B audio tier](<https://huggingface.co/abacusai/Smaug-Audio-Decisions-0.7B>)
- [Source: LiteRT build](<https://huggingface.co/abacusai/Smaug-Decisions-LiteRT>)
- [Source: Maker blog announcement](<https://blog.abacus.ai/blog/2026/11/02/smaug-decisions/>)
- [Source: X announcement: 3 Nov 2026](<https://x.com/bindureddy/status/2117659234448154646>)

## Related projects

No related projects are listed in the registry.