Models
======

Explore all available models and compare their capabilities.

.. _Reasoning_models:

Reasoning models
----------------

- :doc:`Qwen3-0.6B </model_pages/qwen3-0.6b>`
- :doc:`DeepSeek-R1-Distill-Qwen-1.5B </model_pages/deepseek-r1-distill-qwen-1.5b>`

.. _Flagship_chat_models:

Flagship chat models
--------------------

- :doc:`Qwen2.5-0.5B-Instruct </model_pages/qwen2.5-0.5b-instruct>`
- :doc:`Qwen2.5-1.5B-Instruct </model_pages/qwen2.5-1.5b-instruct>`
- :doc:`Qwen2.5-Coder-0.5B-Instruct </model_pages/qwen2.5-coder-0.5b-instruct>`
- :doc:`Llama-3.2-1B-Instruct </model_pages/llama-3.2-1b-instruct>`
- :doc:`openbuddy-llama3.2-1b-v23.1-131k </model_pages/openbuddy-llama3.2-1b-v23.1-131k>`

.. _Multimodal_models:

Multimodal models
-----------------
- :doc:`InternVL2_5-1B-MPO </model_pages/internvl2_5-1b-mpo>`
- :doc:`SmolVLM-256M-Instruct </model_pages/smoivlm-256m-instruct>`
- :doc:`SmolVLM-500M-Instruct </model_pages/smoivlm-500m-instruct>`

Text-to-speech
--------------

Models that can convert text into natural sounding spoken audio.

- :doc:`MeloTTS-English </model_pages/melotts-english>`
- :doc:`MeloTTS-Chinese </model_pages/melotts-chinese>`
- :doc:`MeloTTS-Japanese </model_pages/melotts-japanese>`

Transcription
-------------

Model that can transcribe and translate audio into text.

- :doc:`Whisper-tiny </model_pages/whisper-tiny>`
- :doc:`Whisper-base </model_pages/whisper-base>`
- :doc:`Whisper-small </model_pages/whisper-small>`

Keyword spotting
----------------

Models that can detect specific keywords in audio streams.

- :doc:`Keyword spotting </model_pages/kws>`

Voice activity detection
------------------------

Models that can detect whether there is speech in an audio stream.

- :doc:`Silero-vad </model_pages/silero-vad>`

Automatic Speech Recognition
----------------------------

Models that can convert spoken language into text.

- :doc:`Automatic Speech Recognition </model_pages/asr>`

Vision
------

Models that can process images and perform tasks like object detection, etc.

- :doc:`Yolo11n </model_pages/yolo>`
- :doc:`Depth-Anything-V2 </model_pages/depthanything>`

Model Pages
-----------

.. toctree::
   :maxdepth: 1
   :caption: Model Pages:
   :titlesonly:
   :hidden:

   /model_pages/qwen3-0.6b
   /model_pages/deepseek-r1-distill-qwen-1.5b
   /model_pages/qwen2.5-0.5b-instruct
   /model_pages/qwen2.5-1.5b-instruct
   /model_pages/qwen2.5-coder-0.5b-instruct
   /model_pages/llama-3.2-1b-instruct
   /model_pages/openbuddy-llama3.2-1b-v23.1-131k
   /model_pages/internvl2_5-1b-mpo
   /model_pages/smoivlm-256m-instruct
   /model_pages/smoivlm-500m-instruct
   /model_pages/melotts-english
   /model_pages/melotts-chinese
   /model_pages/melotts-japanese
   /model_pages/whisper-tiny
   /model_pages/whisper-base
   /model_pages/whisper-small
   /model_pages/yolo
   /model_pages/depthanything
   /model_pages/kws
   /model_pages/silero-vad
   /model_pages/asr