---
license: apache-2.0
base_model: google/gemma-2-2b-it
tags:
  - eightly
  - nova
  - gguf
  - gemma2
pipeline_tag: text-generation
---

# Nova Talker 2B

**Nova Talker 2B** is the default conversational voice for [Eight.ly OS](https://eight.ly)'s
built-in AI assistant, **Nova**. It is **Google Gemma 2 2B** (instruction-tuned), quantized to
`Q4_K_M` (~1.6 GB), re-hosted here so an Eight.ly OS install pulls the whole Nova stack from a
single source it controls — no dependency on the public Ollama registry.

## Role in Nova

Nova is **router-in-front**: a single hidden tool router — [Nova Router 1.5B](https://huggingface.co/smashingtags/nova-router-1.5b)
(Qwen2.5-Coder 1.5B, 99% tool-pick accuracy) — decides *which* NAS action to run for **every**
talker. The talker's only job is to write the natural-language reply from the tool's real result.
Nova Talker 2B is the smallest, fastest talker and the default installed on first boot; it runs on
any CPU or GPU.

| Talker | Base | Size | Role |
|--------|------|------|------|
| **Nova Talker 2B** (this repo) | Gemma 2 2B | 1.6 GB | Default voice |
| [Nova Talker 4B](https://huggingface.co/smashingtags/nova-talker-4b) | Qwen 3 4B | 2.4 GB | Optional, richer wording |
| Nova Talker 12B | Gemma 4 12B | 7.0 GB | Premium, GPU-only, experimental |

## License

Apache-2.0. Gemma is distributed under Apache-2.0 (https://ai.google.dev/gemma/apache_2).