AI Agent Hub

LLM Models

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

351 models for "DPO" Compare
Olmo-3-7B-Think logo
Olmo-3-7B-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 7.0B ★ 6.0 ↓ 489.1K
Olmo-3.1-32B-Instruct logo
Olmo-3.1-32B-Instruct
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 ★ 6.0 ↓ 18.7K
Olmo-3-7B-Think-SFT logo
Olmo-3-7B-Think-SFT
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 7.0B ★ 6.0 ↓ 8.5K
LFM2-24B-A2B logo
LFM2-24B-A2B
LiquidAI

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

Open Source 24.0B ★ 6.0 ↓ 3.3K
Hermes-3-Llama-3.1-8B logo
Hermes-3-Llama-3.1-8B
NousResearch

Hermes 3 is the latest version of our flagship Hermes series of LLMs by Nous Research.

Open Source 8.0B ★ 5.0 ↓ 519.5K
Olmo-3-7B-Instruct logo
Olmo-3-7B-Instruct
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 7.0B ★ 5.0 ↓ 473.2K
LFM2.5-1.2B-Instruct logo
LFM2.5-1.2B-Instruct
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 1.2B ★ 5.0 ↓ 115.6K
Olmo-3-7B-Instruct-SFT logo
Olmo-3-7B-Instruct-SFT
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 7.0B ★ 5.0 ↓ 36.5K
EXAONE-4.0-1.2B logo
EXAONE-4.0-1.2B
LGAI-EXAONE

🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 ✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below

Reasoning 1.2B ★ 5.0 ↓ 21.7K
LFM2.5-1.2B-Thinking logo
LFM2.5-1.2B-Thinking
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.

Reasoning 1.2B ★ 5.0 ↓ 8.5K
EXAONE-4.0-1.2B-AWQ logo
EXAONE-4.0-1.2B-AWQ
LGAI-EXAONE

🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 ✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below

Open Source 1.2B ★ 5.0 ↓ 343
EXAONE-4.0-1.2B-FP8 logo
EXAONE-4.0-1.2B-FP8
LGAI-EXAONE

🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 ✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below

Open Source 1.2B ★ 5.0 ↓ 199