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.
Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by…
1.03TA33.3B256K ctx modified-mit322.7K 1.4KJun 2026- Same category
- Larger (1.03T vs 188B)
- Commercial use OK
The package downloads and caches the engine and weights on first use. This repository provides mirage.cact, mirage.safetensors and the model config.
?BApache 2.043.7K 499Nov 2026- Same category
- Commercial use OK
Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding…
27.8B256K ctx Apache 2.02.5M 2.4KApr 2026- Same category
- Smaller (27.8B vs 188B)
- Commercial use OK
- Widely used
Authors: Meta Superintelligence Labs Model Release Date: October 2026 License: Muse Model License
822BA42B1M ctx muse-model-license14.4K 762Sept 2026- Same category
- Larger (822B vs 188B)
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
424BA47B128K ctx Apache 2.0933 107Jun 2025- Same category
- Larger (424B vs 188B)
- 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.
25.8BA4B256K ctx Apache 2.04.9M 1.8KMar 2026- Same category
- Smaller (25.8B vs 188B)
- Commercial use OK
- Widely used
We are delighted to introduce our MiniMax-VL-01 model. It adopts the "ViT-MLP-LLM" framework, which is a commonly used technique in the field of multimodal large language models.
456BA48.8B8K ctx Unknown licence4.3K 287Jan 2025- Same category
- Larger (456B vs 188B)
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
1.03TA33.3B256K ctx modified-mit199K 1.6KApr 2026- Same category
- Larger (1.03T vs 188B)
- Commercial use OK
This family of models performs vision-language and text-only tasks including optical character recognition, multimodal reasoning, localization, common sense reasoning, world knowledge utilization, and coding.
79.4B32K ctx CC BY-NC 4.07.3K 780Sept 2024- Same category
- Smaller (79.4B vs 188B)
We're excited to unveil Qwen2-VL, the latest iteration of our Qwen-VL model, representing nearly a year of innovation.
73.4B32K ctx Qwen License16K 318Sept 2024- Same category
- Smaller (73.4B vs 188B)
Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.
1.03TA33.3B256K ctx modified-mit391.3K 2.9KJan 2026- Same category
- Larger (1.03T vs 188B)
- Commercial use OK
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
27.8B256K ctx Apache 2.01.7M 1.1KFeb 2026- Same category
- Smaller (27.8B vs 188B)
- Commercial use OK
- Widely used
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
424BA47B128K ctx Apache 2.0446 91Jun 2025- Same category
- Larger (424B vs 188B)
- Commercial use OK
Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware.
29.8B128K ctx Apache 2.0153.1K 2.2KAug 2026- Same category
- Smaller (29.8B vs 188B)
- Commercial use OK
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
424BA47B128K ctx Apache 2.0256 26Jun 2025- Same category
- Larger (424B vs 188B)
- Commercial use OK
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 2.02.8K 159Jan 2025- Same category
- Smaller (73.4B vs 188B)
- Commercial use OK
The main purpose of text image correction is to carry out geometric transformation on the image to correct the document distortion, inclination, perspective deformation and other problems in the image, so that the subsequent text recognition can be more accurate.
?BApache 2.0454.3K 14Jun 2025- Same category
- Commercial use OK
Mistral Large 4 is our largest and most capable model to date: a 1 trillion-parameter natively multimodal Mixture-of-Experts model with 49 billion active parameters per token (52 billion including embeddings and output layers), trained from scratch on 3,800 NVIDIA Grace Blackwell GPUs in Mistral's…
1TA52B1M ctx Custom licence19.3K 1.7KSept 2026- Same category
- Larger (1T vs 188B)
The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:
424BA47B128K ctx Apache 2.0235 68Jun 2025- Same category
- Larger (424B vs 188B)
- Commercial use OK
DiffusionGemma is a generative model built by Google DeepMind. Based on the 26B A4B Mixture-of-Experts (MoE) Gemma 4 architecture, DiffusionGemma generates tokens using discrete diffusion. This open-weights model is multimodal, handling text, image, and video inputs to generate text output.
25.8BA4B256K ctx Apache 2.0598.6K 1.3KJun 2026- Same category
- Smaller (25.8B vs 188B)
- Commercial use OK
The Document Image Orientation Classification Module is primarily designed to distinguish the orientation of document images and correct them through post-processing.
?BApache 2.0330.5K 24Jun 2025- Same category
- 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 License218 105Apr 2025- Same category
- Larger (402B vs 188B)
This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
27.8B256K ctx Apache 2.0149.9K 805Aug 2026- Same category
- Smaller (27.8B vs 188B)
- Commercial use OK
The models in this series, including the 4B-parameter end-to-end vision-language model, are presented in the paper Qianfan-OCR: A Unified End-to-End Model for Document Intelligence.
71.8B32K ctx MIT320 40Sept 2025- Same category
- Smaller (71.8B vs 188B)
- Commercial use OK