Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!
The Best TypeScript framework for fine-tuning
Local-first service attribution, stale development server detection, AI runtime health monitoring, and open-weight model capacity planning.
Curated list of open-weight AI models with commercially exploitable licenses, verified benchmarks, and no EU restrictions.
Local LLM·RAG·AI Agent·바이브 코딩을 개념부터 실습과 검증까지 다루는 학습 자료
Run frontier open-weight models privately on NVIDIA DGX Spark.
Benchmark how well any model performs real-world, long-horizon coding tasks across coding agents (harnesses) -- Claude Code and pi. Run models three ways -- Anthropic on Amazon Bedrock, open-weight on Bedrock via a LiteLLM proxy, or self-hosted on EC2 with vLLM -- score them with an LLM judge, and plot the cost/quality Pareto frontier.
“A clean, from-scratch implementation of the OLMo architecture with KV caching, RoPE, and an efficient autoregressive inference pipeline. Designed as a minimal yet extensible foundation for post-training research, including RLHF, preference optimization, and reasoning-focused systems.”
Fine-tune small open models into reliable JSON tool callers. Reproducible, end to end, on a single GPU.
An independent, evidence-graded read on how much you own the open models and inference providers you rely on.
Benchmarking open-weight LLM coding agents as SCOUT delegates: model comparison experiments with pre-registered protocols, blind scoring, and full data.
Curated GLM-5.2 use cases for coding agents, benchmarks, integrations, pricing, local deployment, and real-world limits.
Frontier-Grade Open Weights ── フロンティア級のオープンウェイトモデルは、開かれたのか。Kimi K3 / GLM-5.3 を継続追跡する定点観測型OSS書籍 / They matched the frontier. But no one can hold them. Continuously updated.
Tamper Attack Resistance (BlueDot Impact Technical AI Safety Project)
Open research infrastructure for measuring capability-efficiency tradeoffs in post-trained small open-weight language models.
Policy-enforcing inference for open-weight LLMs. Self-hosted and OpenAI-compatible: enforces your policy at the residual-stream level, so it survives obfuscation, role-play and jailbreak wrappers. Byte-for-byte no-op on in-policy requests.
Local AI lab for llama.cpp model routing, workload aliases, benchmarking, and evaluation through one OpenAI-compatible gateway.
Experimental framework for cross-subtask malicious intent detection in stateless AI agents — research into open-weight model safety
An African AI companion built in Zimbabwe. Open weights, routed inference, grounded in Zimbabwean law and policy. Bundu Foundation IP, sold commercially under Nyuchi Africa.
OpenGauntlet — independent conversational-EQ rankings and sourced voice-AI research for locally hosted models
To associate your repository with the open-weight-models topic, visit your repo's landing page and select "manage topics."