Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 17 of 26

SMALL-LLM★ 2

docker autotrain region:us

llm-finetuning★ 2

docker autotrain region:us

mini-llm★ 2

gradio region:us

tamazight-LLM★ 2

gradio region:us

llm-jp-4-vl-9b-beta★ 2

gradio region:us

qehwa-pashto-llm★ 2

gradio region:us

Mongolian-GPT2★ 2

streamlit region:us

nomic-ai_gpt4all-j-prompt-generations★ 2

static region:us

nomic-ai_gpt4all_prompt_generations★ 2

static region:us

TurkuNLP-gpt3-finnish-3B★ 2

gradio region:us

Dataset-Tokens★ 2

gradio region:us

GPT2-Amharic★ 2

gradio region:us

crowqwen3.5-4b-agent-heretic-gguf★ 2

llama.cpp gguf qwen qwen3.5 coding agent

Agent-Nemotron-ROCmFP6★ 2

gguf quantized rocm rocmfpx agentic tool-calling

Agents-A1-35B-A3B-MXFP4_MOE_Hybrid-Imatrix-GGUF★ 2

transformers gguf qwen qwen3 qwen3.5 moe

Qwen3.6-35B-A3B-Holo3-Qwopus-AgentWorld-qx64-hi-mlx★ 2

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

Qwen-AgentWorld-35B-A3B-4bit-MLX★ 2

mlx safetensors qwen3_5_moe qwen qwen-agentworld quantized

Qwen-AgentWorld-35B-A3B-AutoRound-W4A16-RTN★ 2

safetensors qwen3_5_moe quantized w4a16 autoround low-bit-open-llm-leaderboard

Qwen35-Agent-R2A103★ 2

transformers safetensors gguf qwen3_5_moe image-text-to-text qwen

Agents-A1-Q4_K_S-GGUF★ 2

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

Qwen-AgentWorld-35B-A3B-OptiQ-6bpw-MLX★ 2

mlx safetensors qwen3_5_moe qwen qwen-agentworld quantized

Agents-A1-GPTQ-INT4-Sym★ 2

transformers safetensors qwen3_5_moe image-text-to-text gptq int4

gemma-4-26B-A4B-it-uncensored-GGUF★ 2

gguf abliteration uncensored gemma-4 text-generation en

Arch-Agent-32B-GGUF★ 2

transformers gguf text-generation en base_model:Qwen/Qwen2.5-Coder-32B-Instruct base_model:quantized:Qwen/Qwen2.5-Coder-32B-Instruct

Agents-A1-4B-oQe6★ 2

mlx safetensors qwen3_5 agents agentic reasoning

osmQwopus3.6-27B-Fable-Agentic★ 2

transformers safetensors qwen3_5 image-text-to-text agentic tool-calling

SWE-agent-LM-32B-GGUF★ 2

gguf text-generation en base_model:SWE-bench/SWE-agent-LM-32B base_model:quantized:SWE-bench/SWE-agent-LM-32B license:apache-2.0

Llama-3-Groq-8B-Tool-Use-GGUF★ 2

gguf facebook meta pytorch llama llama-3

Llama-3-Groq-8B-Tool-Use-GGUF★ 2

transformers gguf llama text-generation en base_model:Groq/Llama-3-Groq-8B-Tool-Use

Llama-3-Groq-70B-Tool-Use-GGUF★ 2

transformers gguf llama text-generation en base_model:Groq/Llama-3-Groq-70B-Tool-Use

Granite-4.1-8B-Function-Calling-xLAM-Unsloth-i1-GGUF★ 2

transformers gguf unsloth granite sft fine-tuned

deepseek-coder-1.3b-function-calling-v1★ 2

transformers pytorch gguf llama text-generation conversational

VibeThinker-3B-Function-Calling-xLAM-Unsloth★ 2

transformers safetensors qwen2 text-generation unsloth lora

gemma-2-9b-it-russian-strict-function-calling-DPO★ 2

transformers safetensors gguf gemma2 text-generation conversational

Turkish-Llama-3-8B-function-calling-GGUF★ 2

transformers gguf text-generation-inference unsloth llama trl

Llama-2-7b-chat-hf-function-calling-v3-GGUF★ 2

transformers gguf mistral quantized 2-bit 3-bit

datagemma-rag-27b-it-GGUF★ 2

transformers gguf conversational text-generation base_model:google/datagemma-rag-27b-it base_model:quantized:google/datagemma-rag-27b-it

nash-vicuna-13b-v1dot5-ep2-w-rag-w-simple★ 2

transformers pytorch llama text-generation economics chatgpt

Assistant_Pepe_70B_GPTQ_AR_4-bit-128★ 2

transformers safetensors llama text-generation conversational en

gemma-4-E4B-it-qat-assistant-bf16★ 2

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

gemma-4-31B-it-assistant-fp8★ 2

transformers safetensors gemma4_assistant text-generation gemma4 gemma4-assistant

gemma-4-e2b-yemeni-arabic-assistant-merged-i1-GGUF★ 2

transformers gguf gemma gemma4 unsloth qlora

gemma-4-e2b-yemeni-arabic-assistant-merged-GGUF★ 2

transformers gguf gemma gemma4 unsloth qlora

gemma-4-12B-it-assistant-fp8★ 2

transformers safetensors gemma4_unified_assistant text-generation gemma4 gemma4-assistant

TinyLlama-1.1B-Chat-v1.0-marlin★ 2

transformers safetensors llama text-generation nm-vllm marlin

Yi-1.5-9B-Chat-abliterated★ 2

transformers safetensors llama text-generation llm long context

Mengzi3-8B-Chat★ 2

safetensors llama text-generation conversational zh en

tiny-lm-chat★ 2

transformers pytorch llama text-generation conversational ja

Mistral-7B-v0.1★ 2

pytorch safetensors mistral pretrained text-generation conversational

SDAR-4B-Chat★ 2

transformers safetensors sdar text-generation conversational custom_code

google_txgemma-27b-chat-GGUF★ 2

gguf therapeutics drug-development text-generation en base_model:google/txgemma-27b-chat

Sailor2-3B-Chat★ 2

transformers safetensors qwen2 text-generation multilingual sea

Qwopus3.6-27B-Coder-int4-AutoRound★ 2

transformers safetensors qwen3_5 image-text-to-text text-generation-inference unsloth

Replete-Coder-V2-Llama-3.1-8b-GGUF★ 2

gguf unsloth text-generation en license:apache-2.0 endpoints_compatible

Qwopus3.5-4B-Coder-Fable5-v1-MLX-4bit★ 2

mlx safetensors qwen3_5 mlx-lm apple-silicon fable5

Phi-4-multimodal-instruct★ 2

transformers safetensors phi4mm text-generation nlp code

MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking★ 2

docker region:us

Qwen35B-Agent-R2-Abliterated★ 2

transformers safetensors gguf qwen3_5_moe_text text-generation qwen

shirdel-agent-4b★ 2

nemo safetensors nemotron_h text-generation text-generation-inference transformers

LiquidAI_LFM2-1.2B-RAG-GGUF★ 2

gguf text-generation base_model:LiquidAI/LFM2-1.2B-RAG base_model:quantized:LiquidAI/LFM2-1.2B-RAG endpoints_compatible region:us

gemma-4-26B-A4B-it-qat-assistant-4bit★ 2

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

gemma-4-12B-it-qat-assistant-w4a16-ct★ 2

transformers safetensors gemma4_unified_assistant text-generation compressed-tensors marlin

TinyLlama-1.1B-Chat-v1.0-pruned2.4★ 2

transformers pytorch llama text-generation nm-vllm sparse

PLLuM-4B-chat-2512★ 2

safetensors gemma3 text-generation conversational pl arxiv:2511.03823

Qwen2.5-Coder-3B-Instruct-MLX-4bit★ 2

mlx safetensors qwen2 text-generation conversational base_model:Qwen/Qwen2.5-Coder-3B-Instruct

Agents-A1-4B-kimi-Preview-heretic-GGUF★ 2

transformers gguf agents agents-a1 kimi coding

Agents-A1-4B-kimi-Preview-heretic-GGUF★ 2

gguf agents agents-a1 kimi coding sft

Agents-A1-4B-Fable-Preview-heretic★ 2

transformers safetensors qwen3_5_text text-generation agents agents-a1

OrionStar-Yi-34B-Chat-Llama-GGUF★ 2

transformers gguf llama text-generation base_model:OrionStarAI/OrionStar-Yi-34B-Chat-Llama base_model:quantized:OrionStarAI/OrionStar-Yi-34B-Chat-Llama

SDAR-30B-A3B-Chat★ 2

transformers safetensors sdar_moe text-generation conversational custom_code

llama-2-7b-langchain-chat-gguf★ 2

gguf meta llama llama-2 chinese 7b

falcon2-11B_chat_brainstorm-GGUF★ 2

gguf text-generation dataset:DevQuasar/brainstorm_vicuna_1k base_model:tiiuae/falcon-11B base_model:quantized:tiiuae/falcon-11B license:apache-2.0

mistral-7b-v0.1-layla-v4-chatml-GGUF★ 2

gguf text-generation license:apache-2.0 endpoints_compatible region:us conversational

Llama3-TAIDE-LX-8B-Chat-Alpha1-GGUF★ 2

gguf text-generation base_model:taide/Llama3-TAIDE-LX-8B-Chat-Alpha1 base_model:quantized:taide/Llama3-TAIDE-LX-8B-Chat-Alpha1 license:other endpoints_compatibl

PLLuM-12b-nc-chat-2507★ 2

transformers safetensors mistral text-generation conversational pl

DeepSeek-Coder-V2-Lite-Instruct-GGUF★ 2

gguf text-generation arxiv:2401.06066 base_model:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct base_model:quantized:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct li

KAT-Coder-V2.5-Dev-Q4_K_M-GGUF★ 2

transformers gguf code agent agentic-coding moe

Merlin-Research_Merlin-Agent-GGUF★ 2

gguf merlin-agent quantum-classical quantum-kernel ibm-quantum otoc

lexi-rm-agent★ 2

transformers safetensors gguf qwen2 text-generation ai-model-builder

MiniCPM5-1B-Agentic-Tooluse★ 2

peft safetensors base_model:adapter:openbmb/MiniCPM5-1B lora transformers unsloth

gpt-oss-20b-function-calling-gguf★ 2

gguf quantized gpt-oss multilingual text-generation llama-cpp

Qwen3.6-27B-Fable-Agentic★ 2

transformers safetensors qwen3_5 image-text-to-text agentic tool-calling

Granite-4.1-3B-Function-Calling-xLAM-Unsloth★ 2

transformers safetensors granite text-generation unsloth lora

KAT-Coder-V2.5-Dev-6bit-XL-mlx★ 2

mlx safetensors qwen3_5_moe mlx-vlm moe coding

Granite-4.1-8B-Function-Calling-xLAM-Unsloth★ 2

transformers safetensors granite text-generation unsloth lora

MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16★ 2

transformers safetensors llama text-generation minicpm minicpm5

tn_01_base_coder★ 2

safetensors gguf qwen2 code coding-assistant lora

Mistral-7B-v0.3-Chinese-Chat-uncensored-IQ4_NL-GGUF★ 2

gguf text-generation-inference code unsloth uncensored finetune

ChatBerry-1.1★ 2

safetensors gpt_oss mixture-of-experts mxfp4 text-generation chat

Uncensored_Replete_Coder_Qwen2_1.5b★ 2

gguf text-generation en endpoints_compatible region:us conversational

era-evolve★ 2

FUTS program evolution: evolve a program toward the best score on your metric — 以coding agent为变异算子的程序进化框架

zero★ 2

An open-source AlphaEvolve-style evolutionary algorithm discovery engine. LLM-driven mutation operator inside an island-model evolutionary loop.

DavidAU-Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED★ 2

gradio region:us

MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16-GGUF★ 2

transformers gguf minicpm minicpm5 minicpm5-1b tool-calling

hrm-text-agent-v2★ 2

transformers safetensors hrm_text text-generation function-calling tool-use

Sailor-4B-Chat★ 2

transformers safetensors qwen2 text-generation multilingual sea

ChatBerry-1★ 2

safetensors gpt_oss mixture-of-experts mxfp4 text-generation chat

MetaDiffusion-150M-ChatBase★ 2

safetensors metadiffusion text-generation transformer diffusion-language-model chat

KAT-Coder-V2.5-Dev-NVFP4A16★ 2

safetensors qwen3_5_moe nvfp4 fp4 nvfp4a16 compressed-tensors

Qwen3-4B-Calendar-Agent-SFT★ 2

transformers safetensors qwen3 text-generation tool-calling agents

More in Agent frameworks & infrastructure