AI Agent Hub

LLM Models

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

1,108 models for "Chat" Compare
🤖
EXAONE-Deep-2.4B-AWQ
LGAI-EXAONE

We introduce EXAONE Deep, which exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research. Evaluation results show that 1) EXAONE Deep 2.4B outperforms other models…

Open Source 2.4B ↓ 40
🤖
Klear-46B-A2.5B-Base
Kwai-Klear

🤗 Hugging Face 💻 Github Repository 📑 Technique Report 💬 Issues & Discussions

Open Source 46.0B ↓ 40
🤖
Qwen-SEA-Guard-8B-2602
aisingapore

SEA-Safeguard is a collection of safety-focused Large Language Models (LLMs) built upon the SEA-LION family, designed specifically for the Southeast Asia (SEA) region.

Open Source 8.0B ↓ 38
🤖
distill-bloom-1b3-10x
bigscience

WARNING: This is an intermediary checkpoint and WIP project. It is not fully trained yet. You might want to use Bloom-1B3 if you want a model that has completed training. This model is a distilled version of Bloom-1B3 (10x distillation)

Open Source ↓ 37
🤖
Klear-46B-A2.5B-Instruct
Kwai-Klear

🤗 Hugging Face 💻 Github Repository 📑 Technique Report 💬 Issues & Discussions

Open Source 46.0B ↓ 33
🤖
distill-bloom-1b3
bigscience

WARNING: This is an intermediary checkpoint and WIP project. It is not fully trained yet. You might want to use Bloom-1B3 if you want a model that has completed training. This model is a distilled version of Bloom-1B3

Open Source ↓ 32
🤖
ERNIE-4.5-VL-424B-A47B-Paddle
baidu

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

Multimodal 424.0B ↓ 32
🤖
EXAONE-Deep-32B-AWQ
LGAI-EXAONE

We introduce EXAONE Deep, which exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research. Evaluation results show that 1) EXAONE Deep 2.4B outperforms other models…

Open Source 32.0B ↓ 30
🤖
SmolVLM-Instruct-DPO
HuggingFaceTB

SmolVLM is a compact open multimodal model that accepts arbitrary sequences of image and text inputs to produce text outputs. Designed for efficiency, SmolVLM can answer questions about images, describe visual content, create stories grounded on multiple images, or function as a…

Multimodal ↓ 25
🤖
SOLAR-0-70b-8bit
upstage

This is a 8bit quantized version of upstage/SOLAR-0-70b-16bit

Open Source 70.0B ↓ 23
🤖
Llama-2-13b-chat
meta-llama

Open Source 13.0B ↓ 23
🤖
llama-3-youko-8b-instruct-gptq
rinna

Llama 3 Youko 8B Instruct GPTQ (rinna/llama-3-youko-8b-instruct-gptq)

Open Source 8.0B ↓ 19