AI Agent Hub

LLM Models

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

375 models for "MoE" Compare
🤖
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
nvidia

:--- :--- Total Parameters 550B (55B active) Architecture LatentMoE - Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction (MTP) Context Length Up to 1M tokens Minimum GPU Requirement 8x GB200/B200/GB300/B300, 16x H100, 8x H200 Supported Languages English, French, Spanish…

Open Source 550.0B ★ 38.0 ↓ 296.5K
🤖
Ling-3.0-flash
inclusionAI

🤗 Hugging Face      🤖 ModelScope      🐙 OpenRouter   

Open Source ★ 38.0 ↓ 19.9K
🤖
Ling-3.0-flash-int4
inclusionAI

🤗 Hugging Face      🤖 ModelScope      🐙 OpenRouter   

Open Source ★ 38.0 ↓ 16.6K
🤖
Ling-3.0-flash-fp8
inclusionAI

🤗 Hugging Face      🤖 ModelScope      🐙 OpenRouter   

Open Source ★ 38.0 ↓ 9.2K
🤖
Ling-3.0-flash-fp4
inclusionAI

🤗 Hugging Face      🤖 ModelScope      🐙 OpenRouter   

Open Source ★ 38.0 ↓ 8.7K
🤖
Ling-3.0-flash-base-30T
inclusionAI

🤗 Hugging Face      🤖 ModelScope      🐙 OpenRouter   

Open Source ★ 38.0 ↓ 1.9K
🤖
Ling-3.0-flash-base
inclusionAI

🤗 Hugging Face      🤖 ModelScope      🐙 OpenRouter   

Open Source ★ 38.0 ↓ 1.9K
🤖
Ling-3.0-flash-base-midtrain
inclusionAI

🤗 Hugging Face      🤖 ModelScope      🐙 OpenRouter   

Open Source ★ 38.0 ↓ 1.8K
🤖
MiMo-V2.5-Base
XiaomiMiMo

🤗 HuggingFace   📰 Blog   🎨 Xiaomi MiMo API Platform   🗨️ Xiaomi MiMo Studio  

Open Source ★ 38.0 ↓ 344
🤖
NVIDIA: Nemotron 3 Ultra (free)
nvidia

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Closed Source ★ 38.0
🤖
NVIDIA: Nemotron 3 Ultra (batch)
nvidia

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Closed Source ★ 38.0
🤖
NVIDIA: Nemotron 3 Ultra
nvidia

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Closed Source ★ 38.0