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.
SenseNova-Vision is a unified multimodal model for computer vision. It reformulates heterogeneous visual perception tasks as text generation, image generation, or mixed text-image generation, instead of relying on task-specific heads, decoders, or loss functions for each individual task.
7BCC BY-NC 4.0627 117Jun 2026- Same category
- Smaller (7B vs 16B)
Step-Audio R1.1 (Realtime) is a major upgrade to Step-Audio-R1, designed for interactive spoken dialogue with both real-time responsiveness and strong reasoning capability.
33.5B64K ctx Apache 2.0954 193Jan 2026- Same category
- Larger (33.5B vs 16B)
- Commercial use OK
Youtu-Parsing-Omni is a compact (5B) omni-modal parsing model. Given a single input — a document page, a natural image, a chart / flowchart, a geometry figure, an audio clip or an audio-visual video — it produces one structured JSON envelope that covers both perception (layout elements, text…
5.3B1M ctx youtu-parsing2.5K 132Oct 2026- Same category
- Smaller (5.3B vs 16B)
- Newer release
Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing.
7B16K ctx MIT17.8K 3.7KJan 2025- Same category
- Smaller (7B vs 16B)
- Commercial use OK
Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions.
8B8K ctx MIT846 173Sept 2025- Same category
- Similar size (8B vs 16B)
- Commercial use OK
Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions.
8B8K ctx MIT657 61Sept 2025- Same category
- Similar size (8B vs 16B)
- Commercial use OK
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices.
5.4B32K ctx Gemma Terms of Use25.2K 336Jun 2025- Same category
- Smaller (5.4B vs 16B)
Qwen2-Audio is the new series of Qwen large audio-language models. Qwen2-Audio is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. We introduce two distinct audio interaction modes:
8.4BApache 2.07K 185Jul 2024- Same category
- Similar size (8.4B vs 16B)
- Commercial use OK
🔔 Latest: Emu3.5 Web & Mobile Apps and vLLM offline inference are live — see 🔥 News for details.
34.1B32K ctx Apache 2.0399 176Oct 2025- Same category
- Larger (34.1B vs 16B)
- Commercial use OK
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices.
7.8B32K ctx Gemma Terms of Use733 154Jun 2025- Same category
- Smaller (7.8B vs 16B)
MOSS-Audio is an open-source audio understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.
5.2B40K ctx Apache 2.02.4K 91Apr 2026- Same category
- Smaller (5.2B vs 16B)
- Commercial use OK
RxBrain (Hy-Embodied-RxBrain-1.0) is a unified multimodal foundation model for embodied cognition — a single model that couples language reasoning with visual imagination to deliver three core capabilities:
6.2B256K ctx Apache 2.0311 54Jul 2026- Same category
- Smaller (6.2B vs 16B)
- Commercial use OK
SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
5.1B128K ctx MIT1.2K 19May 2026- Same category
- Smaller (5.1B vs 16B)
- Commercial use OK
Step-Audio-R1 is the first audio language model to successfully unlock Chain-of-Thought (CoT) reasoning. It decisively solves the "inverted scaling" problem that plagues existing models, where performance degrades with longer reasoning.
33.5BApache 2.0119 147Nov 2025- Same category
- Larger (33.5B vs 16B)
- Commercial use OK
We introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction ! By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences.
8.5B9K ctx Apache 2.0765 229Sept 2024- Same category
- Similar size (8.5B vs 16B)
- Commercial use OK
OmniLMM-12B is the most capable version of OmniLMM currently. The model is built based on EVA02-5B and Zephyr-7B-β, connected with a perceiver resampler layer, and trained on multimodal data in a curriculum fashion. The model has three notable features:
12B32K ctx Unknown licence178 74Jan 2024- Same category
- Similar size (12B vs 16B)
MOSS-Audio is an open-source audio understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.
5.2B40K ctx Apache 2.0657 42Apr 2026- Same category
- Smaller (5.2B vs 16B)
- Commercial use OK
This model is Rex-Omni, a 3B-parameter Multimodal Large Language Model (MLLM) presented in the paper "Detect Anything via Next Point Prediction". It is compatible with the Hugging Face transformers library and is licensed under the IDEA License 1.0.
4.1B125K ctx Custom licence14.7K 66Oct 2025- Same category
- Smaller (4.1B vs 16B)
Janus-4o is a multimodal large language model (MLLM) capable of both text-to-image and text-and-image-to-image generation. It is fine-tuned from Janus-Pro-7B using the ShareGPT-4o-Image dataset to align Janus-Pro with GPT-4o image generation capabilities.
7.4B16K ctx MIT123 52Jun 2025- Same category
- Smaller (7.4B vs 16B)
- Commercial use OK
We introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction ! By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences.
8.5B5K ctx Apache 2.0199 30Oct 2024- Same category
- Similar size (8.5B vs 16B)
- Commercial use OK
Shuka v1 is a language model which natively understands audio in Indic languages. It is an encoder-decoder model built by combining two models: - Our state-of-the-art, in-house, audio encoder: Saaras v1 - Meta’s Llama3-8B-Instruct as the decoder
8.7BLlama 3 Community License233 99Aug 2024- Same category
- Similar size (8.7B vs 16B)
Qwen-Audio (Qwen Large Audio Language Model) is the multimodal version of the large model series, Qwen (abbr. Tongyi Qianwen), proposed by Alibaba Cloud. Qwen-Audio accepts diverse audio (human speech, natural sound, music and song) and text as inputs, outputs text.
8.4B2K ctx Unknown licence1.6K 169Nov 2023- Same category
- Similar size (8.4B vs 16B)
Both directories contain model weights and custom Hugging Face Transformers code. The asynchronous Realtime-Venus-Harness and its external tool integrations live in the GitHub repository.
?BApache 2.02.4K 139Sept 2026- Same category
- Commercial use OK
- Newer release
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices.
5.4B32K ctx Gemma Terms of Use614 105Jun 2025- Same category
- Smaller (5.4B vs 16B)