Zero Infrastructure Budget • Live Synced GitHub Stars & Verified API Limits

Free Developer Radar & Open Weights Directory

High-performing open-weights models you can execute locally or access with generous free API tiers. No hidden subscription walls, no fake free trials, with real-time GitHub telemetry.

🤖 Top Open-Weights AI Models (Local Execution & Free APIs)

Reasoning Open-Weights DeepSeek Ollama

Breakthrough open-weights reasoning model with verified chain-of-thought capabilities outperforming commercial closed LLMs on coding and mathematics.

🎁 Free Tier: MIT Licensed weights. Free local execution via Ollama (ollama run deepseek-r1).
Open Repository / Docs ↗

Qwen 2.5 Coder 32B

★ 16,840
Coding Open-Weights Qwen Local-AI

Alibaba Cloud's flagship open-weights coding model supporting 92 languages, repository-scale reasoning, and AST repair.

🎁 Free Tier: Apache-2.0 License. Free local execution via Ollama / vLLM / llama.cpp.
Open Repository / Docs ↗

Llama 3.3 70B Instruct (Meta)

⚡ Verified Free Quota
LLM Open-Weights Meta 128k-Context

Meta's flagship open-weights model delivering GPT-4o-level performance with 128k context window and rich multilingual fluency.

🎁 Free Tier: 100% Free Open Weights. Free cloud API execution via Groq (14.4k req/day) and Together AI.
Open Repository / Docs ↗

Generous Zero-Cost Developer APIs

Groq Cloud Fast LPU Inference API

⚡ Verified Free Quota
Inference API Sub-Second Zero-Cost

Ultra-low latency inference engine powered by custom Language Processing Units (LPUs). Token generation up to 1,200 tokens/sec for open models.

🎁 Free Tier: 14,400 free requests/day (30 RPM) for Llama 3.3 70B, Llama 3.1 8B, and Whisper Large v3.
Open Repository / Docs ↗

Google AI Studio API (Gemini Flash)

⚡ Verified Free Quota
Google Multimodal Free-Tier 1M-Context

Developer API access to Gemini 2.5 and Flash models with native 1M token context window, audio, vision, and multimodal grounding.

🎁 Free Tier: 1,500 requests/day free tier (15 requests/minute) with zero payment method required.
Open Repository / Docs ↗

Cloudflare Workers AI

⚡ Verified Free Quota
Serverless Edge Cloudflare Embeddings

Serverless GPU inference running on Cloudflare's global edge network. Access Llama 3, Mistral, and BGE vector embeddings directly in edge workers.

🎁 Free Tier: 10,000 free Neurons per day across 300+ global edge locations.
Open Repository / Docs ↗

📦 Essential Open Source Infrastructure Repos

Local-AI CLI Runner Go

Get up and running with large language models locally. Lightweight CLI, REST API, and native hardware acceleration across macOS, Linux, and Windows.

🎁 Free Tier: 100% Free Open Source (MIT License). Runs completely offline with zero telemetry.
Open Repository / Docs ↗
PyTorch Foundation HuggingFace Python

Thousands of pretrained models to perform tasks on texts such as classification, information extraction, question answering, and summarization.

🎁 Free Tier: Apache-2.0 License. Canonical ML foundation library.
Open Repository / Docs ↗
Serving High-Throughput Python CUDA

State-of-the-art serving engine utilizing PagedAttention, continuous batching, and chunked prefill. 2-4x higher throughput than standard runtimes.

🎁 Free Tier: Open source (Apache-2.0). Production-grade serving engine for self-hosted clusters.
Open Repository / Docs ↗