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.
Alternatives to LFM3-Omni-2B
114 open-weight models that do the same job as LFM3-Omni-2B (2.2B 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.
Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions. It introduces Dual-Resolution Speech Representations (an efficient 5Hz shared backbone + a 25Hz refined head) to cut compute while keeping high speech quality, and Core-Cocktail training to preserve…
9.5B256K ctx Apache 2.02.2K 194Dec 2025- Same category
- Larger (9.5B vs 2.2B)
- Commercial use OK
GigaChat Audio 10B is an audio-native LLM built on top of the GigaChat 3.1 Lightning text model. A Conformer speech encoder and a modality adapter feed audio embeddings directly into a Mixture-of-Experts decoder, so the model keeps the text quality of its base while adding speech understanding.
10BA1.8B256K ctx MIT789 61Jul 2026- Same category
- Larger (10B vs 2.2B)
- Commercial use OK
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning
5.9BApache 2.046 393Nov 2025- Same category
- Larger (5.9B vs 2.2B)
- 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 MIT847 173Sept 2025- Same category
- Larger (8B vs 2.2B)
- Commercial use OK
This repo contains the PyTorch implementation of Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities. Audio Flamingo 2 achieves the state-of-the-art performance across over 20 benchmarks, with only a 3B parameter small language model.
3BCustom licence0 49Feb 2025- Same category
- Similar size (3B vs 2.2B)
MOSS-Music is an open-source music understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.
9.1B40K ctx Apache 2.0459 45Apr 2026- Same category
- Larger (9.1B vs 2.2B)
- 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 MIT673 61Sept 2025- Same category
- Larger (8B vs 2.2B)
- Commercial use OK
Tar-7B is an open-weight omni model with 8.7B parameters from ByteDance-Seed, published on Hugging Face.
8.7B32K ctx Apache 2.01.7K 41Jul 2025- Same category
- Larger (8.7B vs 2.2B)
- 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 Use737 154Jun 2025- Same category
- Larger (7.8B vs 2.2B)
HyperCLOVA X SEED 8B Omni is a unified multimodal model that brings text, vision, and speech together, based on an auto-regressive Transformer architecture, enabling consistent multimodal understanding and generation.
10.7B8K ctx hyperclovax2.6K 195Dec 2025- Same category
- Larger (10.7B vs 2.2B)
A speech-to-speech model that reasons before it speaks. GLM-4-Voice-9B trained with reinforcement learning against a binary LLM judge on math word problems — no supervised finetuning stage, the reasoning behaviour is learned from the reward alone.
9.5B8K ctx glm-4-voice-license107 20Aug 2026- Same category
- Larger (9.5B vs 2.2B)
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 2.06.7K 185Jul 2024- Same category
- Larger (8.4B vs 2.2B)
- 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 2.0875 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 2.0381 1.1KMay 2026- Same category
- Commercial use OK
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
- Larger (7.4B vs 2.2B)
- Commercial use OK
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.
33BA3B256K ctx nvidia-open-model-agreement93.9K 447Apr 2026- Same category
- Larger (33B vs 2.2B)
- Commercial use OK
SenseNova-U1.5-8B-MoT is our latest native unified multimodal checkpoint for more accurate, consistent, reliable, and aesthetically compelling visual creation.
17.5B256K ctx Apache 2.06.5K 284Aug 2026- Same category
- Larger (17.5B vs 2.2B)
- Commercial use OK
Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:
35.3BA3B64K ctx Apache 2.0340.5K 1.1KSept 2025- Same category
- Larger (35.3B vs 2.2B)
- 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 2.0755 229Sept 2024- Same category
- Larger (8.5B vs 2.2B)
- Commercial use OK
Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:
31.7BA3B64K ctx Apache 2.0150K 343Sept 2025- Same category
- Larger (31.7B vs 2.2B)
- 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 2.030.3K 84Apr 2026- Same category
- Smaller (78M vs 2.2B)
- Commercial use OK
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio-Language Models
?BCustom licence708 163Jul 2025- Same category
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 2.023.9K 138Apr 2026- Same category
- Smaller (79M vs 2.2B)
- Commercial use OK
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
16.3BA1.5B8K ctx Apache 2.02.2K 252Apr 2026- Same category
- Larger (16.3B vs 2.2B)
- Commercial use OK