A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding, Image Generation and Editing.
Alternatives to InternLumina-U2
114 open-weight models that do the same job as InternLumina-U2 (16B omni), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning
5.9BApache 2.063 393Nov 2025- Same category
- Smaller (5.9B vs 16B)
- Commercial use OK
LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: a single end-to-end model that understands text, images, video and audio, and answers in text and speech. It is built for on-device use: one model replaces a separate ASR model, vision-language model, LLM and TTS model.
2.2B125K ctx lfm1.024.6K 722Oct 2026- Same category
- Smaller (2.2B vs 16B)
- Newer release
OmniNeural is the first fully multimodal model designed specifically for Neural Processing Units (NPUs). It natively understands text, images, and audio, and runs across PCs, mobile devices, automobile, IoT, and robotics.
4BCC BY 4.02K 169Aug 2025- Same category
- Smaller (4B vs 16B)
- Commercial use OK
We have developed and released the family Ichigo-llama3s. This family is natively understanding audio and text input.
8B128K ctx Apache 2.051 35Sept 2024- Same category
- Similar size (8B vs 16B)
- Commercial use OK
OmniGen2 is a powerful and efficient unified multimodal model. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. OmniGen2 has competitive performance across four primary capabilities:
4BApache 2.02.3K 461Jun 2025- Same category
- Smaller (4B vs 16B)
- Commercial use OK
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
420M256K ctx Apache 2.0349.2K 203Apr 2026- Same category
- Smaller (420M vs 16B)
- Commercial use OK
We develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal inductive bias beyond the language paradigm.
74.3B128K ctx MIT746 223Mar 2026- Same category
- Larger (74.3B vs 16B)
- Commercial use OK
d1-Omni-2B is a decision model for text, pictures, and audio, built on LFM3-Omni-2B. It returns calibrated answers in one forward pass, without generating tokens.
2.2B125K ctx lfm1.05.9K 125Oct 2026- Same category
- Smaller (2.2B vs 16B)
- Newer release
LFM3-Audio-2B is a compact, fully featured audio model that runs locally on laptops and edge devices. It takes text or audio as input and responds with text, speech, or both.
2B125K ctx lfm1.016.1K 274Sept 2026- Same category
- Smaller (2B vs 16B)
- Newer release
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
470M256K ctx Apache 2.0181.5K 346Apr 2026- Same category
- Smaller (470M vs 16B)
- Commercial use OK
The newly released Ming-flash-omni 2.0 leverages the Ling-2.0 architecture—a Mixture-of-Experts (MoE) framework comprising 100B total and 6B active parameters.
104BA7.5B32K ctx MIT7.6K 282Feb 2026- Same category
- Larger (104B vs 16B)
- Commercial use OK
We introduce MOVA (MOSS Video and Audio), a foundation model designed to break the "silent era" of open-source video generation. Unlike cascaded pipelines that generate sound as an afterthought, MOVA synthesizes video and audio simultaneously for perfect alignment.
?BApache 2.0872 134Jan 2026- Same category
- Commercial use OK
Lance is a 3B native unified multimodal model that supports image and video understanding, generation, and editing within a single framework.
?BApache 2.0384 1.1KMay 2026- Same category
- Commercial use OK
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
423M256K ctx Apache 2.039.1K 149May 2026- Same category
- Smaller (423M vs 16B)
- Commercial use OK
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
78M128K ctx Apache 2.039.3K 83Apr 2026- Same category
- Smaller (78M vs 16B)
- Commercial use OK
d1-omni-600M is a 600M parameter decision model built on LFM2.5-Encoder-350M. You give it a state (text or JSON, with images or a voice clip) and a set of named questions.
587M125K ctx lfm1.09.9K 167Oct 2026- Same category
- Smaller (587M vs 16B)
- Newer release
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio-Language Models
?BCustom licence721 163Jul 2025- Same category
Ming-flash-omni Preview, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100B total parameters, of which only 6B are active per token.
104BA7.6B32K ctx MIT3K 71Oct 2025- Same category
- Larger (104B vs 16B)
- Commercial use OK
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
79M128K ctx Apache 2.025K 137Apr 2026- Same category
- Smaller (79M vs 16B)
- Commercial use OK
OmniParser is a general screen parsing tool, which interprets/converts UI screenshot to structured format, to improve existing LLM based UI agent.
?BMIT1.6K 1.7KOct 2024- Same category
- Commercial use OK
An open full-duplex voice model family that hears your tone and speaks with one. Adventists AI · Apache-2.0 · Recommended: Tag · Flash · Try it online · GitHub
?BApache 2.00 348Nov 2026- Same category
- Commercial use OK
- Newer release
Duo is a full-duplex multimodal world model for real-time audio-visual interaction. This repository contains the four-step distilled Realization weights for Duo 1.0.
?Bminimax-h3-community-license0 10Nov 2026- Same category
- Newer release
Mini-Omni2 is an omni-interactive model. It can understand image, audio and text inputs and has end-to-end voice conversations with users. Featuring real-time voice output, omni-capable multimodal understanding and flexible interaction ability with interruption mechanism while speaking.
?BMIT139 292Oct 2024- Same category
- Commercial use OK
Ultravox is a multimodal Speech LLM built around a pretrained Llama3.2-1B-Instruct and whisper-large-v3-turbo backbone.
683MMIT17.9K 96Feb 2025- Same category
- Smaller (683M vs 16B)
- Commercial use OK