Kyutai Helium 1 2b GGUF

🚀 kyutai/helium-1-2b - GGUF

This repository offers GGUF format model files for kyutai/helium-1-2b, which are quantized with the help of machines provided by TensorBlock. These files are compatible with llama.cpp as of commit b5753.

✨ Features

Supported Languages

The model supports a wide range of languages, including Bulgarian (bg), Czech (cs), Danish (da), German (de), Greek (el), English (en), Spanish (es), Estonian (et), Finnish (fi), French (fr), Irish (ga), Croatian (hr), Hungarian (hu), Italian (it), Lithuanian (lt), Latvian (lv), Maltese (mt), Dutch (nl), Polish (pl), Portuguese (pt), Romanian (ro), Slovak (sk), Slovenian (sl), and Swedish (sv).

Pipeline Tag

It is tagged as a text-generation model.

Base Model

The base model is kyutai/helium-1-2b.

Tags

• TensorBlock
• GGUF

📦 Our projects

Project Name	Description	Image	Link
Forge	An OpenAI-compatible multi-provider routing layer.		Try it now!
Awesome MCP Servers	A comprehensive collection of Model Context Protocol (MCP) servers.		See what we built
TensorBlock Studio	A lightweight, open, and extensible multi-LLM interaction studio.		See what we built

💻 Prompt template

Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.

📚 Model file specification

📦 Downloading instruction

Command line

Step 1: Install Huggingface Client

pip install -U "huggingface_hub[cli]"

Step 2: Download the individual model file to a local directory

huggingface-cli download tensorblock/kyutai_helium-1-2b-GGUF --include "helium-1-2b-Q2_K.gguf" --local-dir MY_LOCAL_DIR

Step 3: Download multiple model files with a pattern

If you want to download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/kyutai_helium-1-2b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

📄 License

The project is licensed under cc-by-sa-4.0.