local

Cross-platform RP client/app with multi-API support, TTS, assets-in-chat, regex filters, and character expressions.

Open (MIT-licensed) reasoning model with distilled 1.5B–70B local checkpoints; known for chain-of-thought quality.

Run Llama Guard 3 locally via Ollama to classify prompts/responses for safety.

Local RWKV manager with a built-in chat UI and OpenAI-compatible API—lean setup for private RP conversations.

Fully open training data, code, and checkpoints; transparent 7B/13B/32B family for reproducible research and apps.

Power-user local frontend for roleplay chats with character cards, lorebooks, multi-model connectors, TTS/vision/image support.

Private, self-hostable chat UI/server (Apache-2.0) supporting local models & Ollama—usable for RP and long-form chats.

Microsoft’s 14B open-weight reasoning model yielding strong complex-task performance with modest hardware.

All-in-one local web UI for LLMs with chat, memory, extensions and RP-friendly presets; runs GGUF/llama.cpp and more.

Open-source local LLM desktop app—download models, chat offline, and customize prompts for RP-style dialogs.

Fully open multimodal (images/video+text) models & training stack; strong results and reproducible recipes.

Modern self-hosted chat UI for local models (Ollama/OpenAI-compatible) with histories, file/RAG, tools—great RP shell.

Character-focused local desktop app (now deprecated) known for no-filter RP; still useful as a reference/shell.

Edge-friendly multimodal 8B model (images/video) with quantized variants for low-VRAM local inference.

Popular desktop app to run and chat with local LLMs; simple model management and fast GPU/CPU offload for RP sessions.