Models

Explore all available models and compare their capabilities.

Reasoning models

• Qwen3-0.6B
• DeepSeek-R1-Distill-Qwen-1.5B

Flagship chat models

• Qwen2.5-0.5B-Instruct
• Qwen2.5-1.5B-Instruct
• Qwen2.5-Coder-0.5B-Instruct
• Llama-3.2-1B-Instruct
• openbuddy-llama3.2-1b-v23.1-131k

Multimodal models

• InternVL2_5-1B-MPO
• SmolVLM-256M-Instruct
• SmolVLM-500M-Instruct

Text-to-speech

Models that can convert text into natural sounding spoken audio.

• MeloTTS-English
• MeloTTS-Chinese
• MeloTTS-Japanese

Transcription

Model that can transcribe and translate audio into text.

• Whisper-tiny
• Whisper-base
• Whisper-small

Keyword spotting

Models that can detect specific keywords in audio streams.

• Keyword spotting

Voice activity detection

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

• Silero-vad

Automatic Speech Recognition

Models that can convert spoken language into text.

• Automatic Speech Recognition

Vision

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

• Yolo11n
• Depth-Anything-V2

Model Pages

• DeepSeek-R1-Distill-Qwen-1.5B
• Qwen3-0.6B
• Qwen2.5-0.5B-Instruct
• Qwen2.5-1.5B-Instruct
• Qwen2.5-Coder-0.5B-Instruct
• Llama-3.2-1B-Instruct
• openbuddy-llama3.2-1b-v23.1-131k
• InternVL2_5-1B-MPO
• SmolVLM-256M-Instruct
• SmolVLM-500M-Instruct
• MeloTTS-English
• MeloTTS-Chinese
• MeloTTS-Japanese
• Whisper-tiny
• Whisper-base
• Whisper-small
• Yolo11n
• Depth-Anything-V2
• Keyword spotting
• Silero-vad
• Automatic Speech Recognition