LongCat-2.5 is a native multimodal MoE model for long-horizon agentic tasks, with 1.6 trillion total parameters and approximately 48 billion activated per token.
Alternatives to LongCat-2.5
120 open-weight models that do the same job as LongCat-2.5 (1.78T 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.
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 License113.1K 174Nov 2025- Same category
- Smaller (957M vs 1.78T)
- 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-1.18.9K 58Oct 2026- Same category
- Smaller (74.9B vs 1.78T)
- Commercial use OK
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
1.3B256K ctx Apache 2.026.3K 33May 2026- Same category
- Smaller (1.3B vs 1.78T)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
8.8B256K ctx Apache 2.0135.1K 234Oct 2025- Same category
- Smaller (8.8B vs 1.78T)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
36BA3B256K ctx Apache 2.040.4K 160Feb 2026- Same category
- Smaller (36B vs 1.78T)
- Commercial use OK
Mage-VL-Cowork A Full Training Recipe to Learn Hybrid Computer Use from Evolved Harnesses
4.7B256K ctx Apache 2.05.3K 230Oct 2026- Same category
- Smaller (4.7B vs 1.78T)
- Commercial use OK
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 License60.9K 261Dec 2025- Same category
- Smaller (8.8B vs 1.78T)
- Commercial use OK
LocateAnything is a vision-language model for fast and high-quality visual grounding, enabling precise object localization, dense detection, and point-based localization across diverse domains in both Enterprise Intelligence and Physical AI.
3.8B32K ctx nvidia-license32.3K 3.2KMar 2026- Same category
- Smaller (3.8B vs 1.78T)
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 2.05.2K 320Oct 2026- Same category
- Smaller (9.7B vs 1.78T)
- Commercial use OK
We are introducing Ling-3.0-flash-VL, our next-generation native multimodal model. Built upon Ling-3.0-flash, it brings visual information into the complete process of understanding, reasoning, acting, and verification—advancing beyond image and video perception to solving real-world tasks through…
125BA5.9B128K ctx MIT7.2K 128Sept 2026- Same category
- Smaller (125B vs 1.78T)
- 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 exaone23.1K 193Apr 2026- Same category
- Smaller (34.4B vs 1.78T)
One Gateway. Every Model. — Route Smarter · Ship Safer · Spend Less.
27.8BApache 2.08.4K 542Aug 2026- Same category
- Smaller (27.8B vs 1.78T)
- Commercial use OK
Qwen-Drive-1.0 retains the architecture of the pretrained Qwen3.5 vision-language model and integrates 3D perception, visual question answering, and motion planning within a unified framework.
4.5BApache 2.07.4K 259Aug 2026- Same category
- Smaller (4.5B vs 1.78T)
- 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.
10.3B128K ctx MIT58K 634Dec 2025- Same category
- Smaller (10.3B vs 1.78T)
- Commercial use OK
Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding.
8.7B36K ctx Apache 2.049.4K 201Dec 2025- Same category
- Smaller (8.7B vs 1.78T)
- Commercial use OK
Intern-Decision-4B is a multimodal structured decision model fine-tuned from Qwen3.5-4B. It accepts a shared state, a schema of named questions, and optional images, and returns an answer distribution for every question in one model forward pass.
4.5B256K ctx Apache 2.05.8K 96Sept 2026- Same category
- Smaller (4.5B vs 1.78T)
- Commercial use OK
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
402BA17B256K ctx Llama 4 Community License211 105Apr 2025- Same category
- Smaller (402B vs 1.78T)
In addition to the original formula, we have further enhanced Qwen2.5-VL-32B's mathematical and problem-solving abilities through reinforcement learning.
33.5B125K ctx Apache 2.0393K 510Mar 2025- Same category
- Smaller (33.5B vs 1.78T)
- Commercial use OK
Apertus 1.5 is a family of 8B and 70B parameter language models designed to advance the state of multilingual, multimodal, fully open, and transparent AI.
8.9BApache 2.09.4K 189Jul 2026- Same category
- Smaller (8.9B vs 1.78T)
- Commercial use OK
Flora-rewarder-27B produces outcome rewards (an episode-level success score), used for monitoring real-world deployments, and process rewards (dense action-quality scores over short time steps), used during reinforcement learning-based post-training.
27.8B256K ctx NVIDIA Non-Commercial License5.5K 23Oct 2026- Same category
- Smaller (27.8B vs 1.78T)
Flora-captioner-27B generates one action instruction for a supplied target interval in a robot or human manipulation video. It uses neighboring video context to disambiguate the intended local operation.
27.4B256K ctx NVIDIA Non-Commercial License5.5K 44Oct 2026- Same category
- Smaller (27.4B vs 1.78T)
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.
12.2B128K ctx Gemma Terms of Use409K 924Mar 2025- Same category
- Smaller (12.2B vs 1.78T)
We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series.
8.5B40K ctx Apache 2.0104.2K 109Aug 2025- Same category
- Smaller (8.5B vs 1.78T)
- Commercial use OK
UI-Venus-2 is a general-purpose foundation GUI agent designed to operate across mobile applications, web platforms, and desktop operating systems through a unified closed-loop reasoning–action framework: the agent observes the current interface, reasons about the task state, executes an action, and…
9B256K ctx Unknown licence6.2K 49Aug 2026- Same category
- Smaller (9B vs 1.78T)