Browse 160,118 AI agents

By IsValorum

T-Search-APEX-I-NanoPlus-GGUF is an open-weight text-generation model published by IsValorum on the Hugging Face Hub. It has 1,001 downloads. Runs with gguf.

By peelsa

phi-4-reasoning-plus-ablit is an open-weight text-generation model published by peelsa on the Hugging Face Hub. It has 779 downloads. Runs with transformers.

By yanggangu

Llama-3.2-1B-Instruct-FT-ScienceQA is an open-weight text-generation model with roughly 1B parameters published by yanggangu on the Hugging Face Hub. It has 501 downloads. Runs with transformers.

By MegaPanchamZ

Qwen3.8-9B-abliterated-25 is an open-weight text-generation model with roughly 9B parameters published by MegaPanchamZ on the Hugging Face Hub. It has 897 downloads. Runs with transformers.

By LLM4Binary

llm4decompile-6.7b-v2 is an open-weight text-generation model with roughly 6.7B parameters published by LLM4Binary on the Hugging Face Hub. It has 593 downloads. Runs with transformers.

By yanggangu

Llama-3.1-8B-Instruct-SMAT-ScienceQA is an open-weight text-generation model with roughly 8B parameters published by yanggangu on the Hugging Face Hub. It has 544 downloads. Runs with transformers.

By Hikaf143

Keural-Cortex-8B-v1.0-1 is an open-weight text-generation model with roughly 8B parameters published by Hikaf143 on the Hugging Face Hub. It has 591 downloads. Runs with transformers.

By CuriosLM

gpt2-124m-fineweb-edu is an open-weight text-generation model with roughly 124M parameters published by CuriosLM on the Hugging Face Hub. It has 725 downloads. Runs with transformers.

By MaziyarPanahi

neural-chat-11b-v3-2-Mistral-7B-Instruct-v0.2-slerp-GGUF is an open-weight text-generation model with roughly 11B parameters published by MaziyarPanahi on the Hugging Face Hub. It has 679 downloads. Runs with transformers.

By phate334

Llama-3-Taiwan-8B-Instruct-Q4_K_M-GGUF is an open-weight text-generation model with roughly 8B parameters published by phate334 on the Hugging Face Hub. It has 1,330 downloads. Runs with transformers.

By SiddhJagani

Qwen3.8-9B-mlx-8Bit is an open-weight text-generation model with roughly 9B parameters published by SiddhJagani on the Hugging Face Hub. It has 703 downloads. Runs with transformers.

By mradermacher

kisoku-1.6b-chat-i1-GGUF is an open-weight text-generation model with roughly 1.6B parameters published by mradermacher on the Hugging Face Hub. It has 3,848 downloads. Runs with transformers.

By Yamada114514

AliceAI-Foundation-80B-A3B-Base-MLX-4bit is an open-weight text-generation model with roughly 80B parameters published by Yamada114514 on the Hugging Face Hub. It has 526 downloads. Runs with mlx.

By AtomicChat

DeepSeek-V4.1-Flash-1017-Uncensored-GGUF is an open-weight text-generation model published by AtomicChat on the Hugging Face Hub. It has 4,774 downloads. Runs with gguf.

By sirfyyn

Katy-27B-GGUF is an open-weight text-generation model with roughly 27B parameters published by sirfyyn on the Hugging Face Hub. It has 1,848 downloads. Runs with gguf.

By Naotaka0127

Kyalulu-Mobile-GGUF is an open-weight text-generation model published by Naotaka0127 on the Hugging Face Hub. It has 854 downloads. Runs with gguf.

By lilcheaty

flint-abliterated-GGUF is an open-weight text-generation model published by lilcheaty on the Hugging Face Hub. It has 2,320 downloads.

By bartowski

DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0-GGUF is an open-weight text-generation model with roughly 1.5B parameters published by bartowski on the Hugging Face Hub. It has 1,026 downloads.

By TheDrainFlorist

Qwen3.5-397B-A17B-VQ-2.6bpw is an open-weight text-generation model with roughly 397B parameters published by TheDrainFlorist on the Hugging Face Hub. It has 879 downloads. Runs with mlx.

By Aaravomega

sarvam-105b-GGUF-IQ2_M-IQ1_M is an open-weight text-generation model with roughly 105B parameters published by Aaravomega on the Hugging Face Hub. It has 2,130 downloads. Runs with gguf.

By InternScience

Sage-A1.5-Q6_K-GGUF is an open-weight text-generation model published by InternScience on the Hugging Face Hub. It has 3,943 downloads. Runs with gguf.

By pgmharikrishnan

Flint-MLX-Serve-4bit is an open-weight text-generation model with roughly 4B parameters published by pgmharikrishnan on the Hugging Face Hub. It has 3,240 downloads. Runs with mlx-serve.

By mtita

Qwen3.8-Flash-Next-CodeUD-v18a-GGUF is an open-weight text-generation model published by mtita on the Hugging Face Hub. It has 1,227 downloads. Runs with gguf.

By Jiunsong

SuperGemma4-31b-abliterated-mlx-4bit is an open-weight text-generation model with roughly 31B parameters published by Jiunsong on the Hugging Face Hub. It has 983 downloads. Runs with mlx.

By AtomicChat

Ling-3.0-flash-Sante-Uncensored-GGUF is an open-weight text-generation model published by AtomicChat on the Hugging Face Hub. It has 2,058 downloads.

By bartowski

RecursiveSI_flint-GGUF is an open-weight text-generation model published by bartowski on the Hugging Face Hub. It has 17,122 downloads.

By ggml-org

DeepSeek-V4-Flash-GGUF is an open-weight text-generation model published by ggml-org on the Hugging Face Hub. It has 1,563 downloads.

By ikedachin

llm-jp-4-8b-thinking_imabari_qa_v4_reasoning_effort_v4 is an open-weight text-generation model with roughly 8B parameters published by ikedachin on the Hugging Face Hub. It has 562 downloads. Runs with transformers.

By dendriteholdings

Ingot-genesis-27B-Q2 is an open-weight text-generation model with roughly 27B parameters published by dendriteholdings on the Hugging Face Hub. It has 14,068 downloads. Runs with gguf.

By hotdogs

jev-Ternary-Bonsai-2-27B-Abliterated-PTQ1_0 is an open-weight text-generation model with roughly 27B parameters published by hotdogs on the Hugging Face Hub. It has 2,532 downloads. Runs with llama.cpp.

By mradermacher

Ministral-3-8B-Claude-Opus-Reasoning-Distilled-i1-GGUF is an open-weight text-generation model with roughly 8B parameters published by mradermacher on the Hugging Face Hub. It has 3,864 downloads. Runs with transformers.

By ReadyArt

Omega-Arsenal-31B-Final-GGUF is an open-weight text-generation model with roughly 31B parameters published by ReadyArt on the Hugging Face Hub. It has 11,290 downloads.

By unsloth

Phi-4-reasoning-plus-GGUF is an open-weight text-generation model published by unsloth on the Hugging Face Hub. It has 9,260 downloads. Runs with transformers.

By llm-jp

llm-jp-4.1-8b-thinking is an open-weight text-generation model with roughly 8B parameters published by llm-jp on the Hugging Face Hub. It has 9,209 downloads. Runs with transformers.

By na0x2c6

Sage-A1.5-GGUF is an open-weight text-generation model published by na0x2c6 on the Hugging Face Hub. It has 28,937 downloads. Runs with gguf.

By windowsxp811203

Qwen3.8-27B-Abliterated-GGUF is an open-weight text-generation model with roughly 27B parameters published by windowsxp811203 on the Hugging Face Hub. It has 10,895 downloads. Runs with gguf.

By VarunHujan

Karna-49M-SFT-Model is an open-weight text-generation model with roughly 49M parameters published by VarunHujan on the Hugging Face Hub. It has 25,880 downloads.

By Hikari07jp

Ternary-Bonsai-2-27B-Abliterated-GGUF is an open-weight text-generation model with roughly 27B parameters published by Hikari07jp on the Hugging Face Hub. It has 32,598 downloads. Runs with llama.cpp.

By sno-ai

Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Cross-vendor peer review, automatic handoff when an agent hits its quota, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup. An open-source AI framework/SDK by sno-ai, hosted on GitHub.

By heqiangdiao-wq

AI 跨境电商运营智能体工具箱 · 把运营 SOP 拆成 7 个可复用的 AI Agent 工作流，含 Prompt、模板与真实案例. An open-source AI framework/SDK by heqiangdiao-wq, hosted on GitHub.

By haidrrrry

Open-source Claude agent skill that teaches Claude Code, Claude Desktop & Claude AI to create and edit professional motion graphics videos with Remotion. AI video editing, B-roll, captions, sound design — from one prompt. An open-source AI framework/SDK by haidrrrry, hosted on GitHub.

By Illyism

SEO skills for Claude Code, Cursor and Codex: SEO autopilot, title tags, blog refreshes, backlinks, customer journeys, video transcripts and copywriting. An open-source AI framework/SDK by Illyism, hosted on GitHub.

By Robinson-AI-Lab

Local-first AI second brain & personal knowledge management: Six-Brain Markdown blueprint, Obsidian example vault, offline deployment and bilingual guides. 六脑方法 · 本地知识管理. An open-source AI framework/SDK by Robinson-AI-Lab, hosted on GitHub.

By DozenTwelve

An AI skill that turns books into animated, narrated, interactive web experiences. An open-source AI framework/SDK by DozenTwelve, hosted on GitHub.

By Inception Labs

Mercury 3 is Inception’s diffusion-based model for fast chat, coding, and agentic workflows, with a 1M-token context window and adjustable reasoning effort. Served through Vercel.

By Moonshot AI

Moonshot AI’s Kimi K3.1 Pro for complex reasoning, coding, and long-context work. Supports image input and a 1M-token context window.

By harims95

An AI-powered application hosted on Hugging Face Spaces by harims95. Built with gradio.

By zk-Armor

An AI-powered application hosted on Hugging Face Spaces by zk-Armor. Built with gradio.