Agent frameworks & infrastructure

Models, fine-tuning & training

2,504 agents · most starred first

Models, fine-tuning & training, page 16 of 26

deepseek-coder-6.7b-chat-and-function-calling-GGUF★ 3

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

gemma-4-12B-it-qat-assistant-4bit★ 3

mlx safetensors gemma4_unified_assistant mlx-vlm gemma-4 gemma-4-12b

Phi-3.5-mini-instruct-python_coding_assistant-GGUF_16bit★ 3

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

gemma4-12b-mtp-assistant★ 3

gguf gemma4 mtp speculative-decoding draft-model llama.cpp

Configurable-Yi-1.5-9B-Chat★ 3

transformers safetensors llama text-generation conversational dataset:vicgalle/configurable-system-prompt-multitask

maestrale-chat-v0.3-beta★ 3

transformers safetensors mistral text-generation sft it

DeepSeek-V2-Lite-Chat-AWQ★ 3

transformers safetensors deepseek_v2 text-generation conversational custom_code

phi-2-chat-turkish-GGUF★ 3

gguf ggml quantized q2_k q3_k_m q4_k_m

moxin-chat-7b-GGUF★ 3

gguf text-generation base_model:moxin-org/Moxin-7B-Chat base_model:quantized:moxin-org/Moxin-7B-Chat license:apache-2.0 endpoints_compatible

Yi-1.5-34B-Chat-16K-GGUF★ 3

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

Qwen1.5-0.5B-Chat-GGUF★ 3

transformers gguf qwen2 text-generation chat en

jais-adapted-7b-chat-GGUF★ 3

gguf Arabic English LLM Decoder causal-lm

Llama-2-13B-Chat-GGUF★ 3

transformers gguf facebook meta pytorch llama

Yi-1.5-9B-Chat-16K-GGUF★ 3

gguf text-generation base_model:01-ai/Yi-1.5-9B-Chat-16K base_model:quantized:01-ai/Yi-1.5-9B-Chat-16K license:apache-2.0 region:us

Yi-1.5-6B-Chat-GGUF★ 3

transformers gguf llama text-generation base_model:01-ai/Yi-1.5-6B-Chat base_model:quantized:01-ai/Yi-1.5-6B-Chat

Gemma-2-9B-Chinese-Chat-GGUF★ 3

transformers gguf gemma2 text-generation en zh

CodeQwen1.5-7B-Chat-GGUF★ 3

transformers gguf qwen2 text-generation chat en

Yi-34B-Chat-GGUF★ 3

transformers gguf llama text-generation base_model:01-ai/Yi-34B-Chat base_model:quantized:01-ai/Yi-34B-Chat

vigogne-2-70B-chat-GGUF★ 3

transformers gguf llama LLM llama-2 finetuned

AceGPT-v2-32B-Chat★ 3

transformers safetensors llama text-generation conversational ar

Qwen2.5-Coder-1.5B-Instruct-bnb-4bit★ 3

transformers safetensors qwen2 text-generation unsloth conversational

Holo-3.1-9B-Coder★ 3

safetensors gguf qwen3_5_text code holo qwen

gemma-4-12b-coder-fable5-composer2.5★ 3

mlx safetensors gemma4_unified image-text-to-text gemma4 coding

Qwopus3.6-27B-Coder-MTP-ROCmFPX★ 3

llama.cpp gguf rocmfpx rocm amd strix-halo

Qwen3-Coder-Next-bf16★ 3

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

Qwen3-Coder-Next-8bit★ 3

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

CodeLlama-13B-MORepair-GGUF★ 3

gguf text-generation base_model:barty/CodeLlama-13B-MORepair base_model:quantized:barty/CodeLlama-13B-MORepair license:llama2 endpoints_compatible

kimi-k2.7-code-eagle3-mla★ 3

safetensors kimi_k2 text-generation speculative-decoding eagle3 eagle3-mla

Qwen2.5-Coder-14B-Q8_0-GGUF★ 3

transformers gguf code qwen qwen-coder codeqwen

DeepSeek-Coder-V2-Lite-Instruct-GGUF★ 3

transformers gguf deepseek_v2 text-generation custom_code base_model:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

qwen3-coder-30b-a3b-debugger-rft★ 3

peft safetensors base_model:adapter:Qwen/Qwen3-Coder-30B-A3B-Instruct lora transformers text-generation

Qwopus3.6-27B-Coder-MTPLX-4bit-Speed★ 3

mlx safetensors qwen3_5 mtplx mtp speculative-decoding

openai-community-gpt2-medium★ 3

static region:us

Jack-Long-Agentic-MTP-27b-IQ4_XS★ 3

gguf iq4_xs qwen3 qwen3.6 agentic long-context

SicariusSicariiStuff_Assistant_Pepe_8B-GGUF★ 3

gguf text-generation en dataset:SicariusSicariiStuff/UBW_Tapestries base_model:SicariusSicariiStuff/Assistant_Pepe_8B base_model:quantized:SicariusSicariiStuff/

Yi-Coder-1.5B-GGUF★ 3

gguf text-generation base_model:01-ai/Yi-Coder-1.5B base_model:quantized:01-ai/Yi-Coder-1.5B license:apache-2.0 endpoints_compatible

Qwen-AgentWorld-35B-A3B-FP8★ 3

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

Qwen3-Coder-Next-6bit★ 3

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

Qwen3-Coder-Next-NVFP4-GB10★ 3

transformers safetensors qwen3_next text-generation qwen3 nvfp4

Hermes-Bonsai-Self-Improving-Agent-Loop★ 3

llama.cpp gguf text-generation base_model:Qwen/Qwen3-8B-Base base_model:quantized:Qwen/Qwen3-8B-Base license:apache-2.0

google_txgemma-9b-chat-GGUF★ 3

gguf therapeutics drug-development text-generation en base_model:google/txgemma-9b-chat

Chat2DB-SQL-7B-GGUF★ 3

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

Llama3-ChatQA-2-8B-GGUF★ 3

gguf nvidia chatqa-2 chatqa llama-3 pytorch

Smol-Llama-101M-Chat-v1-GGUF★ 3

gguf text-generation ggml quantized q2_k q3_k_m

KAT-Coder-V2.5-Dev-ROCmFP4-STRIX-MTP-GGUF★ 3

gguf rocm rocmfp4 strix-halo gfx1151 speculative-decoding

Qwen2.5-Coder-0.5B★ 3

transformers safetensors qwen2 text-generation unsloth code

Jack-Long-Agentic-27b-Prism-8GB-VRAM★ 3

gguf agentic long-context qwen3 prism-quant 1-bit

Agents-A1-4B-cyber-lora★ 3

peft safetensors gguf agents agents-a1 cybersecurity

AgentDoG-Step★ 3

transformers safetensors qwen3 text-generation agent-safety tool-use

CobrIX-1.0-Coder-Flash-33B-A13B★ 3

llama.cpp safetensors qwen35_moe MoE Qwen CobrIX-1.0-Coder-Flash

Qwen2.5-Coder-3B-Instruct-heretic★ 3

transformers safetensors gguf qwen2 text-generation code

Qwen3-Coder-30B-A3B-Instruct-W8A8★ 3

transformers safetensors qwen3_moe text-generation quantized w8a8

Qwen3-4B-Calendar-Agent-RLVR★ 3

transformers safetensors qwen3 text-generation tool-calling function-calling

nlp-models★ 3

A repository for training transformer based models

AgentMercury-Qwen3.5-35B-A3B-SAO★ 3

transformers safetensors qwen3_5_moe image-text-to-text agent tool-use

deepseek-coder-6.7B-kexer-GGUF★ 3

gguf code text-generation dataset:JetBrains/KExercises base_model:deepseek-ai/deepseek-coder-6.7b-base base_model:quantized:deepseek-ai/deepseek-coder-6.7b-base

IBM-Grok4-UltraFast-Coder-1B-GGUF★ 3

transformers gguf granite ibm full-finetune multi-gpu

Qwen2.5-Coder-1.5B-Instruct-GGUF★ 3

transformers gguf code codeqwen chat qwen

DeepSeek-Coder-V2-Instruct-0724-GGUF★ 3

gguf text-generation base_model:deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 base_model:quantized:deepseek-ai/DeepSeek-Coder-V2-Instruct-0724 license:other endpo

Qwen3-Coder-30B-A3B-Instruct-AWQ★ 3

transformers safetensors qwen3_moe text-generation awq w4a16

Qwen2.5-Coder-32B★ 3

transformers safetensors qwen2 text-generation unsloth code

Llama-2-7b-chat-hf-GGUF★ 3

gguf facebook meta pytorch llama llama-2

EventDrivenTD-RL★ 3

Event-driven RL Framework for Long-horizon Control in Asynchronous, Discrete-event Systems

Qwen-7B-Chat-GPTQ★ 3

transformers safetensors qwen text-generation custom_code zh

Tiel-Coder-35B-A3B-Genesis-Hermes-NVFP4-GGUF★ 3

gguf text-generation nvfp4 fp4 moe qwen35moe

salamandra7b_rag_prompt_ca-en-es★ 3

transformers safetensors llama text-generation conversational bg

Arch-Agent-7B-GGUF★ 3

transformers gguf text-generation en base_model:Qwen/Qwen2.5-Coder-7B-Instruct base_model:quantized:Qwen/Qwen2.5-Coder-7B-Instruct

TeenyTinyLlama-460m-Chat★ 3

transformers pytorch jax safetensors llama text-generation

Qwen3.8-27B-Uncensored-Mythos-Class-Agentic★ 3

safetensors qwen3_5 qwen qwen3.8 abliterated uncensored

HarborRL★ 3

An end-to-end framework for Agentic Reinforcement Learning.

qwen3.5-4b-agentic-coder-v4-4bit-mlx★ 3

mlx safetensors qwen3_5 qwen3.5 coding coder

togethercomputer_HybridAgent-14B-Agentic-GGUF★ 3

gguf hybrid-reasoning latent-reasoning agent tool-use text-generation

ZY-S1★ 3

transformers safetensors hrm_text text-generation zyr zy-s1

Sailor2-8B-Chat-GGUF★ 3

gguf mistral quantized 2-bit 3-bit 4-bit

Llama-3.2-SUN-2.5B-chat★ 3

transformers safetensors llama text-generation conversational en

Nusantara-2.7b-Indo-Chat★ 3

transformers safetensors qwen2 text-generation conversational convAI

tora-code-7B-v1.0-GGUF★ 3

transformers gguf llama code math text-generation

veriloop-coder-e2-gguf★ 3

transformers gguf veriloop veriloop-coder code coding-agent

CodeLlama-7B-KStack-GGUF★ 3

transformers gguf code text-generation dataset:JetBrains/KStack base_model:JetBrains/CodeLlama-7B-KStack

Qwen2.5-Coder-1.5B-4bit★ 3

transformers safetensors qwen2 text-generation code qwen

SLCA-GRPO★ 3

SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL — segment-locked credit assignment for tool-calling RL, built on verl.

Falco-Swift★ 3

Distill any LLM into a small, fast, calibrated classifier. A teacher LLM (Claude, Gemini, OpenAI or any compatible API) labels your data with probabilities, a multilingual encoder learns them, and a FastAPI service answers yes/no, choice and score questions in milliseconds, no LLM calls at inference. By Salto Ángel.

mini-agent-v2-GGUF★ 3

gguf quantized qwen2 qwen2.5-coder lora qlora

GPT-OSS-Coder-GGUF★ 3

gguf coding-agent agentic gpt-oss codex llama.cpp

KAT-Coder-V2.5-CMF★ 3

cortiq cmf moe code expert-pruning rust

LM_Agents★ 3

A concise repo for post-training LLM agents with SFT, on-policy distillation and RL fine-tuning on SWE-bench and multi-turn benchmarks.

Udgam-384M-Chat-GGUF★ 3

gguf udgamlabs gemma4 tool-calling function-calling on-device

Nexus-Adapter-Studio★ 3

Nexus Adapter Studio is an experimental browser-based WebGPU application for training LoRA adapters on supported GGUF models. Bring your own model and JSONL corpus, evaluate learning, and export resumable Nexus adapter checkpoints. Runs locally without a Python or PyTorch backend.

codegemma-2b★ 3

transformers safetensors gemma text-generation unsloth bnb

Qwen3.5-9B-C3SM-SDM-Agentic-Coder-Abliterated★ 3

safetensors qwen3_5 abliterated abliterix uncensored creative-writing

Udgam-384M-Chat★ 3

transformers safetensors gemma4_text text-generation udgamlabs gemma4

Llama-3-Groq-8B-Tool-Use★ 3

gradio region:us

Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1★ 3

safetensors qwen2 chat GGUF text-generation conversational

rl-llm★ 2

Reinforcement learning on LLMs in multi-step text-based environments.

chat-bricks★ 2

Chat template support for training.

hermes★ 2

A framework for supervising reinforcement learning agents using large language models.

decision-locator★ 2

Find the layer where a language model commits a decision — and steer it. Any open-weight HF model. (WANDERING arc paper #6)

Fine-tuned-Llama-3-8B-Chatbot★ 2

gradio region:us

teknium_GPT4-LLM-Cleaned★ 2

static region:us

LLM-model-cards★ 2

gradio region:us

More in Agent frameworks & infrastructure