AI Models We Use - All Open Source | Free.ai
Every AI model on Free.ai — all MIT/Apache 2.0 licensed. Qwen, FLUX, Kokoro, Whisper, and more.
audio_separate Models
bg_removal Models
chat Models
Mistral 7B
High-quality 7B model from Mistral AI with excellent instruction following.
by Mistral AIPhi-3 Medium
Microsoft's efficient 14B model with strong reasoning capabilities.
by MicrosoftQwen 2.5 72B
State-of-the-art open-source LLM with 72 billion parameters. Comparable to GPT-4 on many benchmarks.
by Alibaba CloudQwen 2.5 7B
Fast and efficient 7B parameter model for everyday tasks.
by Alibaba Cloudcode Models
Qwen 2.5 Coder 32B
Best open-source code model. Excels at Python, JavaScript, TypeScript, and 50+ languages.
by Alibaba Cloudimage Models
FLUX.1 Schnell
State-of-the-art text-to-image model. Fast generation with stunning quality.
by Black Forest LabsStable Diffusion XL
Industry-standard image generation model with wide community support.
by Stability AIimage_enhance Models
music Models
AudioLDM 2
Generate music from text descriptions. Any genre, mood, or style.
by Haohe LiuMusicGen Medium
Generate music from text descriptions. Any genre, mood, or style.
by Meta (AudioCraft)stt Models
faster-whisper large-v3
CTranslate2 port of OpenAI Whisper. Fast and accurate speech recognition in 99 languages.
by OpenAI / SYSTRANtranslation Models
MadLAD-400 3B
Google's Massive Multilingual Adaptive Dataset translation model. Supports 450+ languages with Apache 2.0 license.
by Googletts Models
video Models
CogVideoX-2B
Text-to-video generation model producing 4-8 second clips.
by Tsinghua UniversityAll models are 100% free to use
Every model on Free.ai is open-source with MIT or Apache 2.0 licensing.
Try Free AI Tools