AI Agent Hub

LLM Models

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

1,109 models for "Chat" Compare
🤖
ERNIE-4.5-300B-A47B-2Bits-Paddle
baidu

The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

Open Source 300.0B ★ 9.0 ↓ 59
🤖
ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle
baidu

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

Open Source 300.0B ★ 9.0 ↓ 54
🤖
ERNIE-4.5-300B-A47B-Base-Paddle
baidu

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

Open Source 300.0B ★ 9.0 ↓ 50
🤖
ERNIE-4.5-300B-A47B-2Bits-TP2-Paddle
baidu

The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

Open Source 300.0B ★ 9.0 ↓ 48
🤖
ERNIE-4.5-300B-A47B-2Bits-TP4-Paddle
baidu

The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

Open Source 300.0B ★ 9.0 ↓ 38
🤖
ERNIE-4.5-300B-A47B-FP8-Paddle
baidu

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

Open Source 300.0B ★ 9.0 ↓ 37
🤖
Llama-3.1-405B-FP8
meta-llama

Open Source 405.0B ★ 8.0 ↓ 488.3K
🤖
Kimi-Linear-48B-A3B-Instruct
moonshotai

Kimi Linear: An Expressive, Efficient Attention Architecture

Open Source 48.0B ★ 8.0 ↓ 185K
🤖
LFM2.5-8B-A1B
LiquidAI

LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

Open Source 8.0B ★ 8.0 ↓ 100K
🤖
Olmo-3.1-32B-Think
allenai

We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding.

Open Source 32.0B ★ 8.0 ↓ 5.7K
🤖
Hermes-3-Llama-3.1-405B
NousResearch

Hermes 3 405B is the latest flagship model in the Hermes series of LLMs by Nous Research, and the first full parameter finetune since the release of Llama-3.1 405B.

Open Source 405.0B ★ 8.0 ↓ 599
🤖
Ring-flash-2.0
inclusionAI

This model is presented in the paper Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model.

Open Source ★ 8.0 ↓ 225