Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 19 of 26

Agents-A1-Q4_K_M-GGUF★ 1

transformers gguf llama-cpp gguf-my-repo text-generation base_model:InternScience/Agents-A1

Agents-A1-oQ6e★ 1

mlx safetensors qwen3_5_moe moe vlm vision

MiniCPM5-1B-Agentic-Tooluse-GGUF★ 1

gguf llama.cpp llama-cpp minicpm minicpm5 minicpm5-1b

Agente-Llama-3.1-Asistant-16bit-v2-GGUF★ 1

transformers gguf p2pclaw cajal autonomous-agent local-ai

Uraion-Agent-Steer-GGUF★ 1

llama.cpp gguf qwen2 qwen2.5 text-generation function-calling

Qwen-AgentWorld-35B-A3B-oQ6-fp16★ 1

transformers safetensors qwen3_5_moe image-text-to-text qwen world-model

Agente-GPT-Qwen2.5-3B-Instruct-Asistant-16bit-v2-GGUF★ 1

transformers gguf p2pclaw cajal autonomous-agent local-ai

merged-llama32-1b-uncensored-dolphin-agent★ 1

transformers safetensors llama text-generation conversational arxiv:1910.09700

Turkish-Llama-3-8B-function-calling-GGUF★ 1

transformers gguf text-generation-inference unsloth llama trl

VibeThinker-3B-Function-Calling-xLAM-Unsloth-GGUF★ 1

gguf llama.cpp quantized unsloth lora trl

Granite-4.1-8B-Function-Calling-xLAM-Unsloth-GGUF★ 1

transformers gguf unsloth granite sft fine-tuned

gemma-2-9b-it-function-calling-GGUF★ 1

transformers gguf conversational gemma2 function-calling trl

Oprel-2b-GUFF★ 1

gguf qwen3_5 OPREL text-generation en base_model:Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

pathlang-1p7b-runE-en30-zh70★ 1

transformers safetensors llama text-generation pretraining language-ordering

gemma-4-31B-it-qat-assistant-bf16★ 1

mlx safetensors gemma4_assistant mlx-vlm gemma-4 gemma-4-31b

gemma-4-31B-it-qat-assistant-mxfp8★ 1

mlx safetensors gemma4_assistant mlx-vlm gemma-4 gemma-4-31b

gemma-4-26B-A4B-it-qat-assistant-mxfp8★ 1

mlx safetensors gemma4_assistant mlx-vlm gemma-4 gemma-4-26b-a4b

gemma-4-26B-A4B-it-qat-assistant-bf16★ 1

mlx safetensors gemma4_assistant mlx-vlm gemma-4 gemma-4-26b-a4b

gemma-4-E4B-it-qat-assistant-4bit★ 1

mlx safetensors gemma4_assistant mlx-vlm gemma-4 gemma-4-e4b

gemma-4-26B-A4B-it-qat-assistant-mxfp4★ 1

mlx safetensors gemma4_assistant mlx-vlm gemma-4 gemma-4-26b-a4b

food-assistant★ 1

transformers safetensors llama text-generation trl sft

food-assistant★ 1

transformers safetensors llama text-generation trl sft

gemma-4-E2B-it-qat-assistant-mxfp4★ 1

mlx safetensors gemma4_assistant mlx-vlm gemma-4 gemma-4-e2b

Assistant_Pepe_32B-mlx-4Bit★ 1

mlx safetensors qwen3 text-generation conversational en

gemma-4-26B-A4B-it-assistant-4bit★ 1

mlx safetensors gemma4_assistant speculative-decoding mtp gemma

internlm2-chat-20b-ExPO★ 1

transformers safetensors internlm2 feature-extraction text-generation conversational

GeM2-Llamion-14B-Chat★ 1

transformers safetensors llama text-generation conversational arxiv:2605.25676

Nous-Hermes-2-SUS-Chat-34B-Slerp★ 1

transformers safetensors llama text-generation merge license:other

Llama3-8B-Chinese-Chat-ExPO★ 1

transformers safetensors llama text-generation conversational en

SDAR-8B-Chat-b32★ 1

transformers safetensors sdar text-generation conversational custom_code

minerva-chat-v0.1-alpha-sft★ 1

transformers safetensors mistral text-generation minerva sft

TinyLlama-1.1B-Chat-v1.0-x2-MoE★ 1

transformers safetensors mixtral text-generation conversational license:apache-2.0

gemma-2-27b-chatml-GGUF★ 1

transformers gguf text-generation base_model:IntervitensInc/gemma-2-27b-chatml base_model:quantized:IntervitensInc/gemma-2-27b-chatml license:gemma

Emollama-chat-13b★ 1

transformers safetensors llama text-generation en arxiv:2401.08508

chattla-20b★ 1

transformers safetensors gguf gpt_oss text-generation tla-plus

katanemo_Arch-Function-Chat-3B-GGUF★ 1

gguf text-generation en base_model:katanemo/Arch-Function-Chat-3B base_model:quantized:katanemo/Arch-Function-Chat-3B license:other

AceGPT-v2-70B-Chat★ 1

transformers safetensors llama text-generation ar zh

OPT-1.3b-Chat★ 1

transformers pytorch safetensors opt text-generation conversational

bofenghuang-vigogne-falcon-7b-chat-gguf★ 1

transformers gguf LLM text-generation fr license:apache-2.0

Trendyol-LLM-7b-chat-v1.0-GGUF★ 1

transformers gguf trendyol llama-2 turkish text-generation

Sailor2-8B-Chat-GGUF★ 1

gguf multilingual sea sailor sft chat

leo-hessianai-70B-chat-GGUF★ 1

transformers gguf llama text-generation en de

ChatHercules-2.5-Mistral-7B-GGUF★ 1

gguf merge mergekit lazymergekit Locutusque/Hercules-2.5-Mistral-7B openchat/openchat-3.5-0106

TinyLlama-1_1B-Chat-v1_0-AQLM-2Bit-1x16-hf★ 1

transformers safetensors llama text-generation conversational arxiv:1910.09700

hippogriff-30b-chat-GGUF★ 1

transformers gguf llama text-generation en dataset:QingyiSi/Alpaca-CoT

Qwen3.6-35B-A3B-mlx-claude-coder-abliterated★ 1

gguf qwen3 qwen3.6 moe coding-agent tool-calling

Qwen2.5-Coder-32B-abliterated-GGUF★ 1

gguf qwen2 abliterated uncensored code qwen2.5

Qwen3-1.7B-Coder-Distilled-SFT★ 1

transformers safetensors qwen3 text-generation causal-lm distillation

Qwen2.5-Coder-32B-abliterated-i1-GGUF★ 1

transformers gguf abliterated uncensored code qwen2.5

Qwen3-Coder-480B-A35B-Instruct-GGUF★ 1

gguf text-generation base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct base_model:quantized:Qwen/Qwen3-Coder-480B-A35B-Instruct endpoints_compatible region:us

North-Mini-Code-1.0-NVFP4★ 1

safetensors cohere2_moe nvfp4 compressed-tensors vllm moe

qwen3-coder-30b-a3b-GGUF★ 1

gguf atomic-chat qwen qwen3 qwen3-coder imatrix

Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx★ 1

transformers safetensors qwen3_5_moe image-text-to-text unsloth qwen3_5

Qwen2.5-Coder-0.5B-Instruct-GPTQ-Int4★ 1

transformers safetensors qwen2 text-generation code codeqwen

kimi-k2.75-code-GGUF★ 1

gguf merge kimi deepseek-v3 moe quantized

Qwopus3.6-27B-Coder-GPTQ-Pro★ 1

transformers safetensors qwen3_5 image-text-to-text qwen3.6 qwopus

Qwen2.5-Coder-7B-Instruct-Q5_K_M-GGUF★ 1

transformers gguf code codeqwen chat qwen

andrewzh_Absolute_Zero_Reasoner-Coder-3b-GGUF★ 1

gguf text-generation base_model:andrewzh/Absolute_Zero_Reasoner-Coder-3b base_model:quantized:andrewzh/Absolute_Zero_Reasoner-Coder-3b endpoints_compatible regi

GLM-5.2-504B-Code-GGUF★ 1

gguf moe reap llama.cpp glm glm-5.2

Qwen2.5-Coder-32B-Instruct-GGUF★ 1

transformers gguf code codeqwen chat qwen

Qwen2.5-Coder-3B-Instruct-Q4_K_M-GGUF★ 1

transformers gguf code codeqwen chat qwen

Qwen2.5.1-Coder-1.5B-Instruct-GGUF★ 1

gguf code codeqwen chat qwen qwen-coder

Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated-GGUF★ 1

gguf llama.cpp ollama gemma4 code coder

supergemma4-26b-abliterated-multimodal-6bit★ 1

mlx safetensors gemma4 mlx-lm quantized 6-bit

IndustrialCoder-32B-FP8★ 1

transformers safetensors iquestcoder text-generation code industrial-ai

Agents-A1-4B-Heretic-ARA-Refusals0-GGUF★ 1

gguf heretic uncensored decensored abliterated ara

Agents-A1-IQ4_NL★ 1

llama.cpp gguf iq4_nl agents moe reasoning

Agents-A1-4B-oQe4★ 1

mlx safetensors qwen3_5 agents agentic reasoning

llama-3.2-1b-mini-agent★ 1

peft safetensors gguf llama llama-3.2 lora

qwen-agentworld-35b-GGUF★ 1

gguf atomic-chat qwen llama.cpp quantized text-generation

Qwen-AgentWorld-35B-A3B-MLX-6bit★ 1

mlx safetensors qwen3_5_moe apple-silicon agentworld 6bit

Agents-A1-4B-MLX-4bit★ 1

mlx safetensors qwen3_5 vlm vision agentic

Qwen-AgentWorld-35B-A3B-JANG_4M★ 1

mlx safetensors qwen3_5_moe qwen world-model agent

gemma-4-12B-agentic-fable5-v2-GGUF★ 1

gguf gemma4 coding agentic terminal tool-use

Qwen-AgentWorld-35B-A3B-heretic★ 1

transformers safetensors qwen3_5_moe image-text-to-text qwen world-model

LFM2.5-1.2B-Thinking-Fable5-hermes-opus-Agent★ 1

transformers safetensors lfm2 text-generation text-generation-inference unsloth

Agents-A1-Q2_K-GGUF★ 1

transformers gguf llama-cpp gguf-my-repo text-generation base_model:InternScience/Agents-A1

SWE-bench.SWE-agent-LM-32B-GGUF★ 1

gguf text-generation base_model:SWE-bench/SWE-agent-LM-32B base_model:quantized:SWE-bench/SWE-agent-LM-32B endpoints_compatible region:us

Granite-4.1-3B-Function-Calling-xLAM-Unsloth-i1-GGUF★ 1

transformers gguf unsloth granite sft fine-tuned

Granite-4.1-3B-Function-Calling-xLAM-Unsloth-GGUF★ 1

transformers gguf unsloth granite sft fine-tuned

Codestral-RAG-19B-Pruned-GGUF★ 1

gguf text-generation endpoints_compatible region:us imatrix

gemma-4-e2b-assistant-gguf★ 1

gguf gemma4 llama.cpp unsloth gemma text-generation

Qwen2-1.5B-Instruct_MOE_CODE_assistant-GGUF_4bit★ 1

gguf qwen2 p2pclaw cajal code-generation-assistant local-ai

Qwen3.5-0.8B-Chat-CoreML★ 1

coreml qwen3_chat qwen3_5 chat text-generation apple-silicon

Poro-34B-chat-GGUF★ 1

gguf text-generation fi en dataset:LumiOpen/instruction-collection-fin license:apache-2.0

Llama3-ChatQA-1.5-8B-IMat-GGUF★ 1

gguf quantized GGUF imatrix quantization imat

Llama3.1-8B-Chinese-Chat-Q4_K_M-GGUF★ 1

transformers gguf llama-factory orpo llama-cpp gguf-my-repo

Llama-PLLuM-8B-chat-2512★ 1

safetensors llama text-generation conversational pl arxiv:2511.03823

MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp-GGUF★ 1

transformers gguf mistral quantized 2-bit 3-bit

Vistral-7B-Chat-imatrix-GGUF★ 1

transformers gguf imatrix Vistral-7B-Chat text-generation en

SeaLLM3-7B-Chat-GGUF★ 1

gguf sea multilingual text-generation en zh

Yi-1.5-34B-Chat-16K-GGUF★ 1

gguf text-generation base_model:01-ai/Yi-1.5-34B-Chat-16K base_model:quantized:01-ai/Yi-1.5-34B-Chat-16K license:other region:us

llama-3-nvidia-ChatQA-1.5-8B-GGUF★ 1

gguf nvidia chatqa-1.5 chatqa llama-3 pytorch

CodeQwen1.5-7B-Chat-GGUF★ 1

gguf chat text-generation en base_model:Qwen/CodeQwen1.5-7B-Chat base_model:quantized:Qwen/CodeQwen1.5-7B-Chat

Qwen1.5-7B-Chat-GGUF★ 1

transformers gguf qwen2 text-generation chat en

TinyLlama-1.1B-Chat-v1.0★ 1

transformers.js onnx llama text-generation kimtos conversational

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-ferocious_quick_worm★ 1

transformers safetensors qwen2 text-generation rl-swarm genrl-swarm

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-slender_nimble_moose★ 1

transformers safetensors qwen2 text-generation rl-swarm genrl-swarm

Qwen3-30B-A3B-Agentic-ToolCaller★ 1

mlx safetensors qwen3_moe lora qwen3 moe

FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth★ 1

transformers safetensors qwen3 text-generation unsloth lora

More in Agent frameworks & infrastructure