Browse 159,125 AI agents

By birgermoell

oellm-9b-256k-stage5-a4b-tool-rl-step48 is an open-weight text-generation model with roughly 9B parameters published by birgermoell on the Hugging Face Hub. It has 766 downloads. Runs with transformers.

By stuchapin

Nanbeige4.3-33B-Base-W8A16-AutoRound is an open-weight text-generation model with roughly 33B parameters published by stuchapin on the Hugging Face Hub. It has 798 downloads. Runs with transformers.

By DarkKitsune

Qwen3.6-Candid-Coder-35B-A3B is an open-weight text-generation model with roughly 35B parameters published by DarkKitsune on the Hugging Face Hub. It has 793 downloads. Runs with transformers.

By AutomatosX

AX-Cyber-Tiel-Coder-35B-A3B-MLX-AXQ-MXFP4-MTP is an open-weight text-generation model with roughly 35B parameters published by AutomatosX on the Hugging Face Hub. It has 836 downloads. Runs with mlx.

By FINAL-Bench

VKORE-325M-NPU-Base is an open-weight text-generation model with roughly 325M parameters published by FINAL-Bench on the Hugging Face Hub. It has 836 downloads. Runs with transformers.

By liuchen88

CLA1.1-27B-MLX is an open-weight text-generation model with roughly 27B parameters published by liuchen88 on the Hugging Face Hub. It has 825 downloads. Runs with mlx.

By aisingapore

Apertus-SEA-LION-v4-8B-IT-GGUF is an open-weight text-generation model with roughly 8B parameters published by aisingapore on the Hugging Face Hub. It has 824 downloads.

By saidutta69

SmolLM2-1.7B-Instruct-heretic is an open-weight text-generation model with roughly 1.7B parameters published by saidutta69 on the Hugging Face Hub. It has 803 downloads. Runs with transformers.

By LuxiaSL

kotodama-tsumugi-1b is an open-weight text-generation model with roughly 1B parameters published by LuxiaSL on the Hugging Face Hub. It has 866 downloads. Runs with pytorch.

By UtopiaIA

MiniCPM5-2B-Elffuss-Code-GGUF is an open-weight text-generation model with roughly 2B parameters published by UtopiaIA on the Hugging Face Hub. It has 842 downloads. Runs with gguf.

By hecan3d

QwenDGAF-Coder-0.5B is an open-weight text-generation model with roughly 0.5B parameters published by hecan3d on the Hugging Face Hub. It has 876 downloads. Runs with gguf.

By luisastellet

qwen-metaphor-unke-camada-18-prompt-numerico is an open-weight text-generation model published by luisastellet on the Hugging Face Hub. It has 916 downloads. Runs with transformers.

By eduardoworrel

alias3-micro-1026-ONNX-decode-only is an open-weight text-generation model published by eduardoworrel on the Hugging Face Hub. It has 911 downloads. Runs with onnxruntime.

By mradermacher

RedSage-Qwen3-8B-DPO-GGUF is an open-weight text-generation model with roughly 8B parameters published by mradermacher on the Hugging Face Hub. It has 1,057 downloads. Runs with transformers.

By enver

rootformer-v15-sovereign-transmute is an open-weight text-generation model published by enver on the Hugging Face Hub. It has 1,112 downloads.

By RedHatAI

Qwen2.5-0.5B-Instruct-quantized.w8a8 is an open-weight text-generation model with roughly 0.5B parameters published by RedHatAI on the Hugging Face Hub. It has 1,110 downloads.

By richardyoung

granite-4.2-3b-heretic-GGUF is an open-weight text-generation model with roughly 3B parameters published by richardyoung on the Hugging Face Hub. It has 1,087 downloads.

By saidutta69

granite-4.1-3b-heretic is an open-weight text-generation model with roughly 3B parameters published by saidutta69 on the Hugging Face Hub. It has 1,182 downloads. Runs with transformers.

By Qwen

Qwen1.5-4B-Chat-GGUF is an open-weight text-generation model with roughly 4B parameters published by Qwen on the Hugging Face Hub. It has 1,168 downloads.

By eduardoworrel

alias3-micro-1026-ONNX is an open-weight text-generation model published by eduardoworrel on the Hugging Face Hub. It has 1,153 downloads. Runs with transformers.js.

By DeepNarra

Paham-Experimental is an open-weight text-generation model published by DeepNarra on the Hugging Face Hub. It has 1,152 downloads.

By mlx-community

Phi-3-mini-4k-instruct-4bit is an open-weight text-generation model with roughly 4B parameters published by mlx-community on the Hugging Face Hub. It has 1,121 downloads. Runs with mlx.

By Husky110

Lunar-Huntress-0.1 is an open-weight text-generation model published by Husky110 on the Hugging Face Hub. It has 1,189 downloads. Runs with transformers.

By bartowski

ReliquaryForge_Teutonic-I-Reliquary-RL-GGUF is an open-weight text-generation model published by bartowski on the Hugging Face Hub. It has 1,470 downloads.

By mmnga-o

ELYZA-Thinking-1.0-llm-jp-4-33b-gguf is an open-weight text-generation model with roughly 33B parameters published by mmnga-o on the Hugging Face Hub. It has 1,551 downloads.

By reaperdoesntknow

Qwen3-0.6B-Distilled-30B-A3B is an open-weight text-generation model with roughly 0.6B parameters published by reaperdoesntknow on the Hugging Face Hub. It has 1,628 downloads. Runs with transformers.

By reaperdoesntknow

Qwen3-1.7B-Distilled-30B-A3B-SFT-GGUF is an open-weight text-generation model with roughly 1.7B parameters published by reaperdoesntknow on the Hugging Face Hub. It has 1,802 downloads. Runs with llama.cpp.

By mradermacher

JEV-9B-GGUF is an open-weight text-generation model with roughly 9B parameters published by mradermacher on the Hugging Face Hub. It has 1,968 downloads. Runs with transformers.

By Luni

Nanbeige-4.3-33B-Heretic-GGUF is an open-weight text-generation model with roughly 33B parameters published by Luni on the Hugging Face Hub. It has 2,137 downloads. Runs with gguf.

By FRENCHFAKER

Nanbeige4.3-33B-cybersec-abliterated-GGUF is an open-weight text-generation model with roughly 33B parameters published by FRENCHFAKER on the Hugging Face Hub. It has 2,868 downloads.

By Goedel-LM

Goedel-Prover-V2-8B is an open-weight text-generation model with roughly 8B parameters published by Goedel-LM on the Hugging Face Hub. It has 2,748 downloads. Runs with transformers.

By Advisio

Radha-9B is an open-weight text-generation model with roughly 9B parameters published by Advisio on the Hugging Face Hub. It has 2,716 downloads. Runs with transformers.

By Alcoft

dnotitia_Smoothie-Qwen3-14B-GGUF is an open-weight text-generation model with roughly 14B parameters published by Alcoft on the Hugging Face Hub. It has 3,201 downloads.

By bartowski

gugujiji_novel-humanize-4b-GGUF is an open-weight text-generation model with roughly 4B parameters published by bartowski on the Hugging Face Hub. It has 3,086 downloads.

By dendriteholdings

Ingot-X-27B-Q2 is an open-weight text-generation model with roughly 27B parameters published by dendriteholdings on the Hugging Face Hub. It has 3,603 downloads. Runs with llama.cpp.

By bartowski

CodeQwen1.5-7B-Chat-GGUF is an open-weight text-generation model with roughly 7B parameters published by bartowski on the Hugging Face Hub. It has 3,450 downloads.

By project-numina

NuminaMath-7B-TIR is an open-weight text-generation model with roughly 7B parameters published by project-numina on the Hugging Face Hub. It has 4,498 downloads. Runs with transformers.

By dendriteholdings

Ingot-VIII-27B-Q2 is an open-weight text-generation model with roughly 27B parameters published by dendriteholdings on the Hugging Face Hub. It has 4,448 downloads. Runs with llama.cpp.

By dendriteholdings

Ingot-V-27B-Q2 is an open-weight text-generation model with roughly 27B parameters published by dendriteholdings on the Hugging Face Hub. It has 5,549 downloads. Runs with llama.cpp.

By ddalcu

Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-4.7bpw is an open-weight text-generation model with roughly 4.7B parameters published by ddalcu on the Hugging Face Hub. It has 4,652 downloads. Runs with mlx-serve.

By manycore-research

SpatialLM-Llama-1B is an open-weight text-generation model with roughly 1B parameters published by manycore-research on the Hugging Face Hub. It has 4,620 downloads. Runs with transformers.

By LiquidAI

LFM3-1.7B is an open-weight text-generation model with roughly 1.7B parameters published by LiquidAI on the Hugging Face Hub. It has 6,311 downloads. Runs with transformers.

By dendriteholdings

Ingot-I-27B-Q2 is an open-weight text-generation model with roughly 27B parameters published by dendriteholdings on the Hugging Face Hub. It has 7,642 downloads. Runs with llama.cpp.

By ReadyArt

Wicked-Stuff-26B-A4B-v2.1-Final-GGUF is an open-weight text-generation model with roughly 26B parameters published by ReadyArt on the Hugging Face Hub. It has 7,458 downloads.

By SC117

Spark-X2.6-4B-abliterated-FIT-GGUF is an open-weight text-generation model with roughly 4B parameters published by SC117 on the Hugging Face Hub. It has 9,460 downloads. Runs with gguf.

By TIGER-Lab

MAmmoTH2-8x7B-Plus is an open-weight text-generation model with roughly 7B parameters published by TIGER-Lab on the Hugging Face Hub. It has 8,683 downloads. Runs with transformers.

By AtomicChat

Nanbeige4.3-33B-GGUF is an open-weight text-generation model with roughly 33B parameters published by AtomicChat on the Hugging Face Hub. It has 16,937 downloads. Runs with gguf.

By fainir

A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work. An open-source AI framework/SDK by fainir, hosted on GitHub.