Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!
Unlimited gpt-oss api openai compatible
GGUF Loader with its Agentic Mode, and floating button, ai Models | Open Source & Offline. Mistral, Deepseek, llama, gemma, qwen
ExpertFingerprinting: Behavioral Pattern Analysis and Specialization Mapping of Experts in GPT-OSS-20B's Mixture-of-Experts Architecture
Four-legged Robot Ensuring Intelligent Sprinkler Automation
En este repositorio encontraras de una forma centralizada y facil, para poder correr alguno de tus modelos favortios localmente usando docker
A curated list of awesome GPT-OSS resources, tools, tutorials, and projects
agentsculptor is an experimental AI-powered development agent designed to analyze, refactor, and extend Python projects automatically. It uses an OpenAI-like planner–executor loop on top of a vLLM backend, combining project context analysis, structured tool calls, and iterative refinement. It has only been tested with gpt-oss-120b via vLLM.
DeepLocal is a clean WPF desktop app that brings DeepL-style translation fully offline via Ollama. Fast two-pane workflow, auto-detect, swap, and model picker (default: gemma3:12b). Build with .NET 8.
Local deployment of gpt-oss-20b model in AWS EC2 instance.
Sample application generated using Opencode and Ollama
A sophisticated red-teaming agent built with LangGraph and Ollama to probe OpenAI's GPT-OSS-20B model for vulnerabilities and harmful behaviors. (Specifically built for the OpenAI Open Model Hackathon)
Universal probing and interpretability tool for MLX language models on Apple Silicon
Co-creating knowledge with AI
A local RAG + web search pipeline with gpt-oss and other similar scale models powered by llama.cpp
[AICI-26] Difficulty-Aware Adaptive Reasoning for Vietnamese VQA with GPT-OSS
GPT-OSS-20B fine-tuned for multilingual reasoning with LoRA (trained on Google Colab GPU). Trained on 1k Multilingual-Thinking samples across multiple languages Features 4-bit quantization and chain-of-thought reasoning. Optimized with Unsloth for efficient training.
Fine-tune GPT-OSS-20B 2x faster using Unsloth and Bright Data. Runs on free Google Colab T4 GPU.
No Hopper architecture (RTX 5090, etc.) required! <16 GB VRAM, Windows.
Add a description, image, and links to the gpt-oss-20b topic page so that developers can more easily learn about it.
To associate your repository with the gpt-oss-20b topic, visit your repo's landing page and select "manage topics."