Hy4 is a new-generation Mixture-of-Experts (MoE) flagship model developed by the Tencent Hy Team, supporting text, image, and video understanding. The language backbone comprises 770B total parameters, of which 49B are activated per token.
Alternatives to Hy4
120 open-weight models that do the same job as Hy4 (774B vision), 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.
WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…
2.4B256K ctx Apache 2.018.2K 87Oct 2026- Same category
- Smaller (2.4B vs 774B)
- Commercial use OK
Model Summary: Granite Vision 4.1 4B is a vision-language model (VLM) that delivers frontier-level performance on structured document extraction tasks — chart extraction, table extraction, and semantic key-value pair extraction — in a compact 4B parameter footprint, providing a lightweight…
4B128K ctx Apache 2.072.1K 114Apr 2026- Same category
- Smaller (4B vs 774B)
- Commercial use OK
d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in one forward pass with zero output tokens.
3.1B32K ctx lfm1.019.7K 511Oct 2026- Same category
- Smaller (3.1B vs 774B)
d1-2B is a decision model for text, pictures, and video, built on LFM3-VL-2B. It returns calibrated answers in one forward pass, without generating tokens.
1.9B125K ctx lfm1.016.8K 335Oct 2026- Same category
- Smaller (1.9B vs 774B)
In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models.
3.8B125K ctx Qwen Research License1.9M 755Jan 2025- Same category
- Smaller (3.8B vs 774B)
- Widely used
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
33.4B256K ctx Apache 2.0217K 261Oct 2025- Same category
- Smaller (33.4B vs 774B)
- 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.
26.5BA4B256K ctx Apache 2.064.8K 479Mar 2026- Same category
- Smaller (26.5B vs 774B)
- Commercial use OK
This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.
108BA14.3B64K ctx MIT15.9K 726Aug 2025- Same category
- Smaller (108B vs 774B)
- Commercial use OK
This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.
108BA14.3B128K ctx MIT6.1K 398Dec 2025- Same category
- Smaller (108B vs 774B)
- Commercial use OK
North Micro Vision Instruct is a 2.4B-parameter open-weight vision-language model with native-resolution image support, released under the Apache 2.0 license. It is designed as a compact foundation for prototyping, task-specific fine-tuning, and specialized multimodal applications.
2.5B500K ctx Apache 2.016.3K 155Aug 2026- Same category
- Smaller (2.5B vs 774B)
- 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.
4.3B128K ctx Gemma Terms of Use1M 1.7KFeb 2025- Same category
- Smaller (4.3B vs 774B)
LFM2.5‑VL-450M is Liquid AI's refreshed version of the first vision-language model, LFM2-VL-450M, built on an updated backbone LFM2.5-350M and tuned for stronger real-world performance. Find more about LFM2.5 family of models in our blog post.
449M125K ctx lfm1.042.6K 240Apr 2026- Same category
- Smaller (449M vs 774B)
Cohere Labs Command A Vision is an open weights research release of a 112 billion parameter model optimized for enterprise image understanding tasks, while keeping a low compute footprint.
112BCC BY-NC 4.09.7K 88Jul 2025- Same category
- Smaller (112B vs 774B)
This section describes the MedGemma model and how to use it.
4.3B128K ctx health-ai-developer-foundations470.4K 1.2KMay 2025- Same category
- Smaller (4.3B vs 774B)
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.
32.7B256K ctx Apache 2.043.1K 610Mar 2026- Same category
- Smaller (32.7B vs 774B)
- Commercial use OK
NVIDIA Nemotron Parse v1.1 is designed to understand document semantics and extract text and tables elements with spatial grounding.
957M9K ctx NVIDIA Open Model License111.5K 174Nov 2025- Same category
- Smaller (957M vs 774B)
- Commercial use OK
NVIDIA Nemotron 3.5 Bolt 74B-A9B is a vision-language model (VLM) designed to run everyday agentic tasks locally. This is the full-precision (BF16) release of this model, intended primarily for customization and post-training rather than direct production inference.
74.9BA9B256K ctx openmdw-1.18.5K 58Oct 2026- Same category
- Smaller (74.9B vs 774B)
- Commercial use OK
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
1.3B256K ctx Apache 2.026.9K 34May 2026- Same category
- Smaller (1.3B vs 774B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
8.8B256K ctx Apache 2.0135.3K 235Oct 2025- Same category
- Smaller (8.8B vs 774B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
36BA3B256K ctx Apache 2.042.5K 160Feb 2026- Same category
- Smaller (36B vs 774B)
- Commercial use OK
Mage-VL-Cowork A Full Training Recipe to Learn Hybrid Computer Use from Evolved Harnesses
4.7B256K ctx Apache 2.05.7K 233Oct 2026- Same category
- Smaller (4.7B vs 774B)
- Commercial use OK
- Newer release
SenseNova-Loop-9B-Preview is a multimodal language model developed for long-context and agentic workflows. It accepts text and images and generates text for applications that combine document understanding, coding, and interaction with external tools.
9.7B256K ctx Apache 2.05.7K 322Oct 2026- Same category
- Smaller (9.7B vs 774B)
- Commercial use OK
We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality.
34.4B256K ctx exaone23.8K 193Apr 2026- Same category
- Smaller (34.4B vs 774B)
NVIDIA Cosmos Reason 2 is an open, customizable, 8B-parameter reasoning vision language model (VLM) for physical AI and robotics that enables robots and vision AI agents to reason like humans, using prior knowledge, physics understanding and common sense to understand and act in the real world.
8.8B256K ctx NVIDIA Open Model License60K 265Dec 2025- Same category
- Smaller (8.8B vs 774B)
- Commercial use OK