Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
- localllm
Repository Index
77,353 visible repositories in the index
217–240 of 880 · Most stars
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Modeling, training, eval, and inference code for OLMo
Efficient Triton Kernels for LLM Training
- llm-training
- triton
- finetuning
- gemma2
A lightweight LMM-based Document Parsing Model
TranslatedFirefly: a large model training tool that supports training large models such as Qwen2.5, Qwen2, Yi1.5, Phi-3, Llama3, Gemma, MiniCPM, Yi, Deepseek, Orion, Xverse, Mixtral-8x7B, Zephyr, Mistral, Baichuan2, Llma2, Llama, Qwen, Baichuan, ChatGLM2, InternLM, Ziya2, Vicuna, Bloom, etc.
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
- ai
- genkit
- vector-database
- embedders
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
An open, programmable decision layer for models and compute.
- mixture-of-models
- semantic-router
- vllm
- ai-gateway
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
- ai-agent
- agent-os
- llm-orchestration
- agentic-ai
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
- adk
- agent-development-kit
- agents
- coding-agent
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
- metric-learning
- deep-learning
- computer-vision
- machine-learning
Main reference implementation for NLWeb, implemented in Python.
an ambient intelligence library
SWE-bench: Can Language Models Resolve Real-world Github Issues?
- benchmark
- language-model
- software-engineering
GPT Image 2/2.5/2.6 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
- agent-skills
- gpt-image-2
- image-generation
- image-prompt
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Translated🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. A large language model based on Chinese legal knowledge
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
- chinese
- computer-vision
- multi-modal-learning
- nlp
Solve Visual Understanding with Reinforced VLMs
- deepseek-r1
- grpo
- llm
- multimodal
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
- llama
- llamacpp
- llm-inference
- ollama-api
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
🐢 Open-Source Evaluation & Testing library for LLM Agents
- mlops
- ml-validation
- ml-testing
- ai-testing
Democratizing Reinforcement Learning for LLMs
- agent-framework
- agentic-workflow
- distributed-training
- llm-training