AI Agent Hub

LLM Models

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

1,108 models for "Chat" Compare
🤖
StripedHyena-Nous-7B
togethercomputer

One of the focus areas at Together Research is new architectures for long context, improved training, and inference performance over the Transformer architecture. Spinning out of a research program from our team and academic collaborators, with roots in signal processing-inspired…

Open Source 7.0B ↓ 180
🤖
JanusCoder-14B
internlm

💻Github Repo • 🤗Model Collections • 📜Technical Report

Code 14.0B ↓ 180
🤖
Intern-S1-mini-FP8
internlm

💻Github Repo • 🤗Model Collections • 📜Technical Report • 💬Online Chat

Open Source ↓ 180
🤖
Qwen-SEA-LION-v4-32B-IT-4BIT
aisingapore

Qwen-SEA-LION-v4-32B-IT-4BIT (GPTQ model)

Open Source 32.0B ↓ 177
🤖
japanese-stablelm-instruct-alpha-7b-v2
stabilityai

"A parrot able to speak Japanese, ukiyoe, edo period" — Stable Diffusion XL

Open Source 7.0B ↓ 176
🤖
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
🤖
Medical-GPT-OSS-Swallow-120B
tokyotech-llm

Medical-GPT-OSS-Swallow-120B is a medical-domain language model based on tokyotech-llm/GPT-OSS-Swallow-120B-RL-v0.1. It is designed to support research and development toward safe and trustworthy AI for Japanese clinical settings.

Open Source 120.0B ↓ 175
🤖
llama-65b-instruct
upstage

Developed by : Upstage Backbone Model : LLaMA Variations : It has different model parameter sizes and sequence lengths: 30B/1024, 30B/2048, 65B/1024 Language(s) : English Library : HuggingFace Transformers License : This model is under a Non-commercial Bespoke License and governe…

Open Source 65.0B ↓ 175
🤖
internlm2-chat-1_8b-sft
internlm

💻Github Repo • 🤔Reporting Issues • 📜Technical Report

Open Source 8.0B ↓ 173
🤖
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
🤖
SmolVLM2-2.2B-Base
HuggingFaceTB

This is the base model for SmolVLM2-2.2B, a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text…

Multimodal 2.2B ↓ 167