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-base
120 open-weight models that do the same job as Hy4-base (771B 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.
Step3 is our cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning.
321B64K ctx Apache 2.048.6K 166Jul 2025- Same category
- Smaller (321B vs 771B)
- 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.
402BA17B1M ctx Llama 4 Community License13.9K 528Apr 2025- Same category
- Similar size (402B vs 771B)
dots3-note preview is the first open-weight model in the dots3 family. It is a Mixture-of-Experts model with 280B total parameters, 16B activated parameters, and support for a context length of up to 512K tokens. The model can understand text, images, video, and audio, and produces text outputs.
288BA25.1B512K ctx Apache 2.04.2K 296Aug 2026- Same category
- Smaller (288B vs 771B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
236BA22B256K ctx Apache 2.0318K 430Sept 2025- Same category
- Smaller (236B vs 771B)
- Commercial use OK
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
- Similar size (456B vs 771B)
apex-flash-1-abliterated is an experimental derivative of apex-flash-1, Cantina Security's open-weights security model developed in partnership with Yeta (@yetalabs on X).
321BA18.3B1M ctx MIT707 51Sept 2026- Same category
- Smaller (321B vs 771B)
- 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 2.0933 107Jun 2025- Same category
- Similar size (424B vs 771B)
- Commercial use OK
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
236BA22B256K ctx Apache 2.081.5K 421Sept 2025- Same category
- Smaller (236B vs 771B)
- 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 2.0446 91Jun 2025- Same category
- Similar size (424B vs 771B)
- Commercial use OK
Command A+ is an open source model with 25 billion active parameters and 218B total parameters model optimized for agentic, multilingual, and reasoning-heavy tasks with a focus on enterprise performance, while also providing support for vision inputs for processing image inputs.
219BA25.5B200K ctx Apache 2.014.3K 148May 2026- Same category
- Smaller (219B vs 771B)
- 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
- Similar size (424B vs 771B)
- Commercial use OK
Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.
220B1M ctx tencent-hy-license2.1K 350Nov 2026- Same category
- Smaller (220B vs 771B)
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
- Similar size (424B vs 771B)
- Commercial use OK
💻Github Repo • 🤗Model Collections • 📜Technical Report • 💬Online Chat
241BA27.8B64K ctx Apache 2.030K 257Jul 2025- Same category
- Smaller (241B vs 771B)
- 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
Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model that combines a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding.
201B256K ctx Apache 2.09.6K 463May 2026- Same category
- Smaller (201B vs 771B)
- 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
- Similar size (402B vs 771B)
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
125BA10B256K ctx Apache 2.0737.5K 658Feb 2026- Same category
- Smaller (125B vs 771B)
- Commercial use OK
Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.
219B1M ctx tencent-hy-license489 24Nov 2026- Same category
- Smaller (219B vs 771B)
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is the full-precision release of NVIDIA Nemotron 3.5 Super VL, a vision-language model for reasoning, coding, tool use, document understanding, and video understanding.
124BA12B1M ctx openmdw-1.184.9K 133Oct 2026- Same category
- Smaller (124B vs 771B)
- 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
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
Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
27.8B256K ctx Apache 2.06.6M 20.7KAug 2026- Same category
- Smaller (27.8B vs 771B)
- Commercial use OK
- Widely used
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.
188BApache 2.0813 43Nov 2026- Same category
- Smaller (188B vs 771B)
- Commercial use OK