Models
28 matched .
Explore AI models for text, images, audio and coding. Filter by model task, open or closed weights, and Hugging Face availability.
All types
Text · 2,080
Image · 398
Video · 224
Audio · 372
Coding · 40
Multimodal · 885
Structured data · 27
3D · 17
Weights and source · filters active
Explore other catalogs
Saved only in this browser. No account needed.
How to choose models
Start with the task you need the model to perform, then narrow the model type and weight availability. Open weights do not automatically mean unrestricted commercial use. Check the original model card for the license, input requirements, evaluation results and hardware needs before choosing a model.
-
Mellum2 12B A2.5B Base
JetBrains
Mellum2-12B-A2.5B-Base is JetBrains’ Apache 2.0 text-generation base model, a 12B MoE checkpoint wi…
Coding · Closed
2k
HF downloads
-
North Mini Code 1.0
Cohere
North Mini Code 1.0 is Cohere’s Apache 2.0 agentic coding model with 30B total parameters and 3B ac…
Coding · Closed
12k
HF downloads
-
Composer 2 Anysphere Composer 2 is Cursor’s frontier coding model optimized for high intelligence per dollar, built to s… Coding · Closed Closed weights
-
D4RT Google D4RT is DeepMind’s unified 4D scene reconstruction and tracking model that turns ordinary videos in… Coding · Closed Closed weights
-
Fugu Max Sakana AI Fugu Max is Sakana AI's cost-optimized multi-agent orchestration model, dynamically routing each ta… Coding · Closed Closed weights
-
Fugu Ultra v2 Sakana AI Fugu Ultra v2 is Sakana AI's capability-focused multi-agent orchestrator for complex multi-step rea… Coding · Closed Closed weights
-
Fugu-Ultra v1.1 Sakana AI Fugu-Ultra is a multi-agent orchestration model that dynamically coordinates a pool of frontier AI… Coding · Closed Closed weights
-
Gemini 3.5 Flash Cyber Google Gemini 3.5 Flash Cyber is a lightweight cybersecurity model built on Gemini 3.5 Flash and fine tune… Coding · Closed Closed weights
-
Gemini 3.8 Flash Cyber Google DeepMind Gemini 3.8 Flash Cyber is a cybersecurity focused variant of Gemini 3.8 Flash, built for vulnerabil… Coding · Closed Closed weights
-
GPT 5.1 Codex OpenAI GPT 5.1 Codex is a code-focused variant that maps specs to working code, writes diffs and tests, an… Coding · Closed Closed weights
-
GPT 5.1 Codex High OpenAI GPT 5.1 Codex High trades a bit of speed for higher accuracy on complex coding tasks. It performs d… Coding · Closed Closed weights
-
GPT 5.2 Codex OpenAI GPT-5.2-Codex is OpenAI’s frontier agentic coding model based on GPT-5.2, optimized for long-horizo… Coding · Closed Closed weights
-
GPT 5.3 Codex OpenAI GPT-5.3-Codex is OpenAI’s most capable agentic coding model, combining GPT-5.2-Codex’s frontier cod… Coding · Closed Closed weights
-
GPT 5.3 Codex Spark OpenAI GPT-5.3-Codex-Spark is OpenAI’s first real-time coding model, a smaller GPT-5.3-Codex variant that… Coding · Closed Closed weights
-
Laguna M.1 poolside Laguna M.1 is a 225B total parameter (23B activated) Mixture-of-Experts model built for agentic cod… Coding · Closed Closed weights
-
MAI Code 1 Flash
Microsoft
MAI-Code-1-Flash is Microsoft AI’s 5B inference-efficient agentic coding model integrated into GitH…
Coding · Closed
Closed
weights
-
MAI Cyber 1 Flash
Microsoft
MAI Cyber 1 Flash is Microsoft's first cybersecurity model, built to find complex vulnerabilities i…
Coding · Closed
Closed
weights
-
Muse Code Meta Platforms Muse Code is a terminal based AI coding agent from Meta that plans changes, writes code, and valida… Coding · Closed Closed weights
-
Muse Spark 1.2 Meta Platforms Muse Spark 1.2 is a coding focused model from Meta, an update to Muse Spark 1.1 with improved code… Coding · Closed Closed weights
-
Muse Spark 1.3 Meta Platforms Muse Spark 1.3 is Meta's agentic coding model, built for longer horizon, tool using workflows. It m… Coding · Closed Closed weights
-
Navigator n2
Yutori
Navigator n2 is Yutori's 27B parameter frontier computer use model, built to operate full desktop e…
Coding · Closed
Closed
weights
-
SWE 1.7
Cognition
SWE 1.7 is Cognition's most capable coding model to date, reaching frontier level intelligence at a…
Coding · Closed
Closed
weights
-
SWE 2
Cognition
SWE-2 is Cognition's agentic coding model built for autonomous software engineering, post-trained f…
Coding · Closed
Closed
weights
-
v0 1.0 md
Vercel
v0-1.0-md is Vercel's original composite AI coding model for the v0 platform. It combines Anthropic…
Coding · Closed
Closed
weights
-
v0 1.5 lg
Vercel
v0-1.5-lg is Vercel's larger composite AI coding model for full-stack web app generation. It pairs…
Coding · Closed
Closed
weights
-
v0 1.5 md
Vercel
v0-1.5-md is a composite AI coding model from Vercel that generates full-stack web application code…
Coding · Closed
Closed
weights
-
Voyage code 2
Voyage AI
voyage-code-2 is an embedding model optimized for semantic code retrieval. It supports a 16,000-tok…
Coding · Closed
Closed
weights
-
Voyage code 3
Voyage AI
Text embedding model optimized for code retrieval. Supports Matryoshka embeddings at 256, 512, 1024…
Coding · Closed
Closed
weights