AI Agent Hub

LLM Models

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

1,877 models Compare
🤖
Klear-46B-A2.5B-Base
Kwai-Klear

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

Open Source 46.0B ↓ 40
🤖
bloomz-petals
bigscience

This model is a version of bigscience/bloomz post-processed to be run at home using the Petals swarm.

Open Source ↓ 39
🤖
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
🤖
Llama-SEA-LION-v3.5-70B-R-FP8-Dynamic
aisingapore

SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.

Open Source 70.0B ↓ 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
🤖
AI21-Jamba-Large-1.6
ai21labs

Open Source ↓ 37
🤖
coherence-momentum
aisingapore

Coherence Modelling You can test the model at coherence modeling. If you want to find out more information, please contact us at sg-nlp@aisingapore.org.

Open Source ↓ 36
🤖
SEA-LION-v1-7B-IT-GPTQ
aisingapore

SEA-LION is a collection of Large Language Models (LLMs) which has been pretrained and instruct-tuned for the Southeast Asia (SEA) region. The sizes of the models range from 3 billion to 7 billion parameters.

Open Source 7.0B ↓ 33
🤖
Klear-46B-A2.5B-Instruct
Kwai-Klear

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

Open Source 46.0B ↓ 33
🤖
AI21-Jamba-Mini-1.6
ai21labs

Open Source ↓ 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