Browse 160,118 AI agents

By vmarcelo

Sabi-Noema-IQ3_S-GSQ-RCO-GGUF is an open-weight text-generation model published by vmarcelo on the Hugging Face Hub. It has 856 downloads. Runs with llama.cpp.

By nvidia

AceReason-Nemotron-14B is an open-weight text-generation model with roughly 14B parameters published by nvidia on the Hugging Face Hub. It has 814 downloads. Runs with transformers.

By iromu

LFM2.5-230M-tools is an open-weight text-generation model with roughly 230M parameters published by iromu on the Hugging Face Hub. It has 772 downloads. Runs with transformers.

By TokenTinkerer

Cyber-Tiel-Coder-35B-A3B-MTP-TTQ-GGUF is an open-weight text-generation model with roughly 35B parameters published by TokenTinkerer on the Hugging Face Hub. It has 4,499 downloads. Runs with llama.cpp.

By adzcai

AfriGuardInst-tiny-aya-global-lora-merged is an open-weight text-generation model published by adzcai on the Hugging Face Hub. It has 794 downloads. Runs with transformers.

By Neelectric

OLMo-2-1124-7B-Instruct_SFT_mathv00.07 is an open-weight text-generation model with roughly 7B parameters published by Neelectric on the Hugging Face Hub. It has 870 downloads. Runs with transformers.

By gabriellarson

OpenReasoning-Nemotron-1.5B-GGUF is an open-weight text-generation model with roughly 1.5B parameters published by gabriellarson on the Hugging Face Hub. It has 935 downloads. Runs with transformers.

By nkthebass

tinybrainbot-3m-loop is an open-weight text-generation model with roughly 3M parameters published by nkthebass on the Hugging Face Hub. It has 1,324 downloads. Runs with transformers.

By lmstudio-community

Qwen2.5-32B-Instruct-MLX-8bit is an open-weight text-generation model with roughly 32B parameters published by lmstudio-community on the Hugging Face Hub. It has 879 downloads. Runs with mlx.

By codavidgarcia

Qwen3.8-27B-OrcaRouter-Uncensored-MTP-GGUF is an open-weight text-generation model with roughly 27B parameters published by codavidgarcia on the Hugging Face Hub. It has 1,503 downloads. Runs with gguf.

By JIAN-PENG

qwen-instruct-coutdown_deepseek_r1 is an open-weight text-generation model published by JIAN-PENG on the Hugging Face Hub. It has 930 downloads. Runs with transformers.

By second-state

Gemma-2b-it-GGUF is an open-weight text-generation model with roughly 2B parameters published by second-state on the Hugging Face Hub. It has 963 downloads. Runs with transformers.

By RedHatAI

Laguna-XS.2-NVFP4 is an open-weight text-generation model published by RedHatAI on the Hugging Face Hub. It has 1,396 downloads. Runs with vllm.

By WaveCut

Flint-UD-Q4_K_XL-NInfer-v3 is an open-weight text-generation model published by WaveCut on the Hugging Face Hub. It has 1,942 downloads. Runs with ninfer.

By TheBloke

Nanbeige-16B-Chat-GGUF is an open-weight text-generation model with roughly 16B parameters published by TheBloke on the Hugging Face Hub. It has 957 downloads. Runs with transformers.

By bench-labs

cagliostro-v3.5 is an open-weight text-generation model published by bench-labs on the Hugging Face Hub. It has 1,060 downloads. Runs with transformers.

By QuantFactory

internlm2-math-plus-1_8b-GGUF is an open-weight text-generation model with roughly 8B parameters published by QuantFactory on the Hugging Face Hub. It has 1,068 downloads.

By nvidia

AceReason-Nemotron-1.1-7B is an open-weight text-generation model with roughly 7B parameters published by nvidia on the Hugging Face Hub. It has 1,395 downloads. Runs with transformers.

By bartowski

Naphula_Cyberdonia-24B-v8-GGUF is an open-weight text-generation model with roughly 24B parameters published by bartowski on the Hugging Face Hub. It has 1,883 downloads.

By turintech

Qwen3.5-9B-Artemis-GGUF is an open-weight text-generation model with roughly 9B parameters published by turintech on the Hugging Face Hub. It has 1,182 downloads. Runs with gguf.

By ReliquaryForge

Teutonic-I-Reliquary-RL is an open-weight text-generation model published by ReliquaryForge on the Hugging Face Hub. It has 8,605 downloads. Runs with transformers.

By Lordnyx

qwen3.5-9b-triple-loop-fase2 is an open-weight text-generation model with roughly 9B parameters published by Lordnyx on the Hugging Face Hub. It has 1,405 downloads.

By grevinden

qwen3.8-27b-w4a16-autoround-rtx3090 is an open-weight text-generation model with roughly 27B parameters published by grevinden on the Hugging Face Hub. It has 7,695 downloads. Runs with compressed-tensors.

By internlm

internlm2-math-plus-7b is an open-weight text-generation model with roughly 7B parameters published by internlm on the Hugging Face Hub. It has 1,437 downloads. Runs with transformers.

By mradermacher

supergemma4-e4b-abliterated-GGUF is an open-weight text-generation model with roughly 4B parameters published by mradermacher on the Hugging Face Hub. It has 1,728 downloads. Runs with transformers.

By lmstudio-community

Qwen2.5-7B-Instruct-MLX-4bit is an open-weight text-generation model with roughly 7B parameters published by lmstudio-community on the Hugging Face Hub. It has 2,608 downloads. Runs with mlx.

By mradermacher

K2-Horizon-3.7B-Claude-Opus-Reasoning-Distilled-i1-GGUF is an open-weight text-generation model with roughly 3.7B parameters published by mradermacher on the Hugging Face Hub. It has 3,068 downloads. Runs with transformers.

By SakanaAI

TinySwallow-1.5B-Instruct-GGUF is an open-weight text-generation model with roughly 1.5B parameters published by SakanaAI on the Hugging Face Hub. It has 2,069 downloads. Runs with transformers.

By bartowski

nvidia_Llama-3.1-Nemotron-Nano-8B-v1-GGUF is an open-weight text-generation model with roughly 8B parameters published by bartowski on the Hugging Face Hub. It has 2,534 downloads.

By ReadyArt

Wicked-Stuff-12B-GGUF is an open-weight text-generation model with roughly 12B parameters published by ReadyArt on the Hugging Face Hub. It has 4,127 downloads.

By openbmb

BitCPM-CANN-3B-unquantized is an open-weight text-generation model with roughly 3B parameters published by openbmb on the Hugging Face Hub. It has 3,224 downloads. Runs with transformers.

By meshllm

DeepSeek-V4-Flash-UD-Q4_K_XL-layers is an open-weight text-generation model published by meshllm on the Hugging Face Hub. It has 1,700 downloads. Runs with mesh-llm.

By mradermacher

LYNX-ALPHA-i1-GGUF is an open-weight text-generation model published by mradermacher on the Hugging Face Hub. It has 3,906 downloads. Runs with transformers.

By nur-dev

farabi-0.6B-agent-rag is an open-weight text-generation model with roughly 0.6B parameters published by nur-dev on the Hugging Face Hub. It has 10,913 downloads. Runs with transformers.

By QuantFactory

Peach-2.0-9B-8k-Roleplay-GGUF is an open-weight text-generation model with roughly 9B parameters published by QuantFactory on the Hugging Face Hub. It has 5,011 downloads.

By hendrimardani

fine-tuned-model-indonesian-2 is an open-weight text-generation model published by hendrimardani on the Hugging Face Hub. It has 4,573 downloads. Runs with transformers.

By h2oai

h2ogpt-4096-llama2-70b-chat is an open-weight text-generation model with roughly 70B parameters published by h2oai on the Hugging Face Hub. It has 17,517 downloads. Runs with transformers.

By orcarouter

DeepSeek-V4.1-Flash-1017-abliterated-GGUF is an open-weight text-generation model published by orcarouter on the Hugging Face Hub. It has 27,056 downloads. Runs with gguf.

By google

gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant is an open-weight text-generation model with roughly 26B parameters published by google on the Hugging Face Hub. It has 6,816 downloads. Runs with transformers.

By legraphista

internlm2-math-plus-7b-IMat-GGUF is an open-weight text-generation model with roughly 7B parameters published by legraphista on the Hugging Face Hub. It has 6,040 downloads. Runs with gguf.

By mobilint

HyperCLOVAX-SEED-Text-Instruct-1.5B is an open-weight text-generation model with roughly 1.5B parameters published by mobilint on the Hugging Face Hub. It has 27,925 downloads. Runs with transformers.

By mobilint

EXAONE-Deep-2.4B is an open-weight text-generation model with roughly 2.4B parameters published by mobilint on the Hugging Face Hub. It has 27,384 downloads. Runs with transformers.

By Abiray

DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-IQ2_XXS-GGUF is an open-weight text-generation model published by Abiray on the Hugging Face Hub. It has 74,853 downloads.

By TheStageAI

gemma-4-E4B-it-GGUF is an open-weight text-generation model with roughly 4B parameters published by TheStageAI on the Hugging Face Hub. It has 12,071 downloads. Runs with llama.cpp.

By IsValorum

Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF is an open-weight text-generation model with roughly 27B parameters published by IsValorum on the Hugging Face Hub. It has 10,329 downloads. Runs with gguf.

By unsloth

Qwen2.5-Coder-7B-Instruct-bnb-4bit is an open-weight text-generation model with roughly 7B parameters published by unsloth on the Hugging Face Hub. It has 58,054 downloads. Runs with transformers.

By unsloth

Qwen2.5-32B-Instruct-bnb-4bit is an open-weight text-generation model with roughly 32B parameters published by unsloth on the Hugging Face Hub. It has 46,361 downloads. Runs with transformers.

By unsloth

Qwen2.5-7B-Instruct-unsloth-bnb-4bit is an open-weight text-generation model with roughly 7B parameters published by unsloth on the Hugging Face Hub. It has 85,250 downloads. Runs with transformers.