AI Agent Hub

LLM Models

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

1,304 models for "Transformer" Compare
🤖
Qwen2.5-Coder-1.5B-Instruct
Qwen

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings…

Code 1.5B ↓ 773K
🤖
gemma-2-2b-it
google

Open Source 2.0B ↓ 764.6K
🤖
SmolLM3-3B-Base
HuggingFaceTB

1. Model Summary 2. How to use 3. Evaluation 4. Training 5. Limitations 6. License

Open Source 3.0B ↓ 761.2K
🤖
DeepSeek-Coder-V2-Lite-Instruct
deepseek-ai

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

Code ↓ 717.8K
🤖
GOT-OCR2_0
stepfun-ai

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Multimodal 0.58B ↓ 701.6K
🤖
gemma-2-9b-it
google

Open Source 9.0B ↓ 693.9K
🤖
Phi-3.5-vision-instruct
microsoft

Phi-3.5-vision is a lightweight, state-of-the-art open multimodal model built upon datasets which include - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data both on text and vision. The model belongs to the Phi-3 mo…

Multimodal 4.2B ↓ 681K
🤖
HunyuanOCR
tencent

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

Multimodal 1.0B ↓ 674.4K
🤖
UI-TARS-1.5-7B
ByteDance-Seed

--- license: apache-2.0 language: - en pipeline tag: image-text-to-text tags: - multimodal - gui library name: transformers ---

Multimodal 7.0B ↓ 672.8K
🤖
Kimi-K2.6
moonshotai

🤗   huggingchat     📰   Tech Blog

Open Source ↓ 647.5K
🤖
Florence-2-large
microsoft

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Multimodal 0.77B ↓ 642.4K
🤖
phi-4
microsoft

------------------------- ------------------------------------------------------------------------------- Developers Microsoft Research Description phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acqu…

Open Source ↓ 632.2K