11 models · ranked by HuggingFace downloads
Gemma 4-E4B-IT is Google DeepMind's edge-optimized 4-billion-parameter any-to-any multimodal model from the Gemma 4 family, designed for deployment on mobile and edge devices rather than servers. The 'any-to-any' pipeline_tag indicates multimodal input and output capability beyond standard image-text-to-text. Apache 2.0 licensed.
gemma-4-E2B-it is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
gemma-4-E4B is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
OneThinker-SFT-Qwen3-8B is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
Qwen3-Omni-30B-A3B-Instruct is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
Qwen2.5-Omni-3B is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
Qwen2.5-Omni-7B is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
gemma-4-E4B-it-MLX-4bit is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
gemma-4-E4B-it-MLX-8bit is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.
gemma-4-E4B-it-MLX-6bit is an open-source any-to-any model available on HuggingFace. Details are sourced from the public model registry.