AI Agent Hub

LLM Models

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

1,294 models for "Transformer" Compare
🤖
EXAONE-4.5-33B-FP8
LGAI-EXAONE

We introduce EXAONE 4.5, the first open-weight vision language model developed by LG AI Research. Integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, we expand the model's capability toward multimodality. EXAONE 4.5 features 33 billion parameters in tot…

Open Source 33.0B ★ 21.0 ↓ 3K
🤖
Aurora-Spec-Qwen3-Coder-Next-FP8
togethercomputer

This is an EAGLE3 draft model trained from scratch (random initialization) using the Aurora inference-time training framework for speculative decoding. Unlike traditional approaches that fine-tune pre-trained models, this model is built entirely through Aurora's online training p…

Code ★ 21.0 ↓ 152
🤖
Qwen3.5-4B
Qwen

[!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.

Open Source 4.0B ★ 20.0 ↓ 7.4M
🤖
North-Mini-Code-1.0
CohereLabs

North Mini Code is an open weights research release of a 30B-A3B parameter model optimized for code generation, agentic software engineering, and terminal tasks.

Code ★ 20.0 ↓ 21.5K
🤖
granite-4.2-8b
ibm-granite

--- --- Developers Granite Team, IBM Model Type Decoder-only Dense Transformer (Reasoning) Architecture GraniteForCausalLM Base Model Granite-4.1-8B-Base Parameters 8B Context Length Natively Supports 128K (Long-context extension to 512K) Precision bfloat16 Tested Languages Engli…

Open Source 8.0B ★ 20.0 ↓ 9K
🤖
North-Mini-Code-1.0-fp8
CohereLabs

North Mini Code is an open weights research release of a 30B-A3B parameter model optimized for code generation, agentic software engineering, and terminal tasks.

Code ★ 20.0 ↓ 1.5K
🤖
North-Mini-Code-1.0-w4a16
CohereLabs

North Mini Code is an open weights research release of a 30B-A3B parameter model optimized for code generation, agentic software engineering, and terminal tasks.

Code ★ 20.0 ↓ 1.1K
🤖
Mistral: Devstral 2 2512
mistralai

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

Closed Source ★ 19.0
🤖
Kimi-K2-Thinking
moonshotai

Kimi K2 Thinking is the latest, most capable version of open-source thinking model. Starting with Kimi K2, we built it as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and oth…

Open Source ★ 17.0 ↓ 43.1K
🤖
LongCat-Flash-Lite
meituan-longcat

Model Introduction We introduce LongCat-Flash-Lite, a non-thinking 68.5B parameter Mixture-of-Experts (MoE) model with approximately 3B activated parameters, supporting a 256k context length through the YaRN method. Building upon the LongCat-Flash architecture, LongCat-Flash-Lite…

Open Source ★ 17.0 ↓ 15.4K
🤖
LongCat-Flash-Lite-FP8
meituan-longcat

Model Introduction We introduce LongCat-Flash-Lite, a non-thinking 68.5B parameter Mixture-of-Experts (MoE) model with approximately 3B activated parameters, supporting a 256k context length through the YaRN method. Building upon the LongCat-Flash architecture, LongCat-Flash-Lite…

Open Source ★ 17.0 ↓ 14.3K
🤖
gpt-oss-20b
openai

Try gpt-oss · Guides · Model card · OpenAI blog

Open Source 20.0B ★ 15.0 ↓ 6.5M