Agnes 2.5 Pro Theta is a multimodal mixture-of-experts checkpoint distributed with its model implementation, tokenizer, chat template, and image/video processors. This release provides BF16 weights for local inference through Transformers.
Alternatives to Agnes-2.5-Pro-Theta
120 open-weight models that do the same job as Agnes-2.5-Pro-Theta (188B 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.
QVQ-72B-Preview is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities.
73.4B125K ctx Qwen License1.7K 613Dec 2024- Same category
- Smaller (73.4B vs 188B)
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
36BA3B256K ctx Apache 2.042K 160Feb 2026- Same category
- Smaller (36B vs 188B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
33.4B256K ctx Apache 2.0217.3K 261Oct 2025- Same category
- Smaller (33.4B vs 188B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
31.1BA3B256K ctx Apache 2.0432.4K 629Sept 2025- Same category
- Smaller (31.1B vs 188B)
- Commercial use OK
Clef is a 27B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass.
27.4B256K ctx Apache 2.078.2K 2.4KSept 2026- Same category
- Smaller (27.4B vs 188B)
- Commercial use OK
The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text \+ images in / text out).
88.6B128K ctx Llama 3.2 Community License420 370Sept 2024- Same category
- Smaller (88.6B vs 188B)
How do I pronounce the model's name? Watch a Youtube tutorial
80B2K ctx Custom licence9.1K 188Jul 2023- Same category
- Smaller (80B vs 188B)
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 2.043.8K 609Mar 2026- Same category
- Smaller (32.7B vs 188B)
- 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 exaone23.4K 193Apr 2026- Same category
- Smaller (34.4B vs 188B)
💻Github Repo • 🤗Model Collections • 📜Technical Report • 💬Online Chat
917BA22.9B256K ctx Apache 2.011K 277Feb 2026- Same category
- Larger (917B vs 188B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
9.7B256K ctx Apache 2.06.4M 2.4KFeb 2026- Same category
- Smaller (9.7B vs 188B)
- Commercial use OK
- Widely used
Molmo is a family of open vision-language models developed by the Allen Institute for AI. Molmo models are trained on PixMo, a dataset of 1 million, highly-curated image-text pairs. It has state-of-the-art performance among multimodal models with a similar size while being fully open-source.
73.3B4K ctx Apache 2.01.3K 299Sept 2024- Same category
- Smaller (73.3B vs 188B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
2.3B256K ctx Apache 2.05.5M 492Feb 2026- Same category
- Smaller (2.3B vs 188B)
- Commercial use OK
- Widely used
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 2.0360.8K 510Mar 2025- Same category
- Smaller (33.5B vs 188B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
4.7B256K ctx Apache 2.04.6M 1.3KFeb 2026- Same category
- Smaller (4.7B vs 188B)
- Commercial use OK
- Widely used
UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities.
73.4B32K ctx Apache 2.0249 25Jan 2025- Same category
- Smaller (73.4B vs 188B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
873M256K ctx Apache 2.02.7M 852Feb 2026- Same category
- Smaller (873M vs 188B)
- Commercial use OK
- Widely used
MiniCPM-V 4.7 is the latest model in the MiniCPM-V series, available in a 1B variant. It builds on the family's single-image, multi-image, and video understanding capabilities, combining stronger foundation capabilities with efficient visual encoding and on-device inference.
1.6B256K ctx Apache 2.0470.5K 418Oct 2026- Same category
- Smaller (1.6B vs 188B)
- Commercial use OK
We introduce InternVL2.5-MPO, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. This series builds upon InternVL2.5 and Mixed Preference Optimization.
78.4B32K ctx Qwen License129 55Dec 2024- Same category
- Smaller (78.4B vs 188B)
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
8.8B256K ctx Apache 2.06.2M 1.3KOct 2025- Same category
- Smaller (8.8B vs 188B)
- Commercial use OK
- Widely used
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 2.066.6K 477Mar 2026- Same category
- Smaller (26.5B vs 188B)
- Commercial use OK
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.
771BA50.3B1M ctx tencent-hy-license68 8Nov 2026- Same category
- Larger (771B vs 188B)
- Newer release
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window.
2.78T1M ctx kimi-k3734.2K 12KJun 2026- Same category
- Larger (2.78T vs 188B)
AesCode generates information-rich visual artifacts such as slides, posters, and dashboards as HTML/CSS. The output remains structured, editable, and verifiable, but the task poses a distinct challenge: code models cannot see how layout, hierarchy, and color come together on the canvas.
33.4B256K ctx Apache 2.01.4K 59Sept 2026- Same category
- Smaller (33.4B vs 188B)
- Commercial use OK