AI Agent Hub

LLM Models

Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.

377 models for "MoE" Compare
🤖
ERNIE-4.5-21B-A3B-Base-PT
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Open Source 21.0B ↓ 226
🤖
AquilaMoE-SFT
BAAI

AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies Language Foundation Model & Software Team Beijing Academy of Artificial Intelligence (BAAI) [Paper(released soon)] [Code] [github]

Open Source ↓ 199
🤖
AquilaDense-16B
BAAI

AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies Language Foundation Model & Software Team Beijing Academy of Artificial Intelligence (BAAI) [Paper(released soon)] [Code] [github]

Open Source 16.0B ↓ 176
🤖
Ring-lite
inclusionAI

Ring-lite is a lightweight, fully open-sourced MoE (Mixture of Experts) LLM designed for complex reasoning tasks. It is built upon the publicly available Ling-lite-1.5 model, which has 16.8B parameters with 2.75B activated parameters.. We use a joint training pipeline combining k…

Open Source ↓ 172
🤖
Step-3.5-Flash-Base-Midtrain
stepfun-ai

Step 3.5 Flash (visit website) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. We also open-sourced the training codebase (SteptronOss), with support for continue pretrain, SFT, RL (W…

Open Source ↓ 168
🤖
LongCat-Flash-Prover
meituan-longcat

We introduce LongCat-Flash-Prover , a flagship $560$-billion-parameter open-source Mixture-of-Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose the native formal reasoning task into three independent f…

Open Source ↓ 146
🤖
LongCat-Flash-Thinking
meituan-longcat

We introduce and release LongCat-Flash-Thinking , which is a powerful and efficient large reasoning model (LRM) with 560 billion total parameters, featuring an innovative Mixture-of-Experts (MoE) architecture. The model incorporates a dynamic computation mechanism that activates…

Open Source ↓ 134
🤖
LongCat-Flash-Thinking-ZigZag
meituan-longcat

[2026.1.28] We have provided the TileLang kernels supporting prefill (chunked-prefill as well) and decode (multi-token prediction as well). The full attention version is placed at flash mla interface.py while the streaming sparse attention version is placed at streaming sparse at…

Open Source ↓ 91
🤖
LongCat-Flash-Chat-FP8
meituan-longcat

Model Introduction We introduce LongCat-Flash, a powerful and efficient language model with 560 billion total parameters, featuring an innovative Mixture-of-Experts (MoE) architecture. The model incorporates a dynamic computation mechanism that activates 18.6B∼31.3B parameters (a…

Open Source ↓ 88
🤖
LongCat-HeavyMode-Summary
meituan-longcat

We introduce an updated version of LongCat-Flash-Thinking, named LongCat-Flash-Thinking-2601, a powerful and efficient Large Reasoning Model (LRM) with 560 billion total parameters, built upon an innovative Mixture-of-Experts (MoE) architecture.

Open Source ↓ 75
🤖
ERNIE-4.5-VL-424B-A47B-Base-Paddle
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Multimodal 424.0B ↓ 64
🤖
ERNIE-4.5-0.3B-Base-Paddle
baidu

[!NOTE] Note: " -Paddle " models use PaddlePaddle weights, while " -PT " models use Transformer-style PyTorch weights.

Open Source 0.3B ↓ 58