๐ Overview
rrchat AI is an open-source initiative focused on high-efficiency, private local AI: combining compact bilingual (RU/EN) reasoning models with native mobile interfaces.
Our goal is to bring sovereign intelligence directly into your workflow โ zero cloud telemetry, maximum throughput on consumer hardware, and seamless orchestration between mobile devices and local GPU workstations.
๐ง Models: RR-Gen1 Series
The RR-Gen1 lineup spans from ultra-fast 1.7B edge assistants to a 9B agentic flagship, optimized for agentic tool use, mathematical reasoning, and competitive coding:
| Model | Size / Active | Base Architecture | Primary Strengths | Recommended VRAM | Weights & GGUF |
|---|---|---|---|---|---|
| Viper-9B (Flagship) | 9B | Qwen3.5-9B | Competitive Coding (LCB 33%), Agentic Tool Calling, Math CoT, R-Tuning Honesty | ~8โ12 GB | Base ยท GGUF |
| Cerberus-E4B | 4B (7.5B Total) | Gemma 4-E4B | Balanced Multi-Task Reasoning, Native Gemma Tool Schemas, Multimodal | ~4โ8 GB | Base ยท GGUF |
| Mercury-1.7B | 1.7B | LFM3-VL-2B | Extreme Speed (~180โ200 t/s), Linear Attention + Short-Conv, SigLIP Vision | ~2โ4 GB | Base ยท GGUF |
| Mercury-Acad-1.7B | 1.7B | LFM3-VL-2B | Academic & Scientific Reasoning, Mathematical CoT, STEM Domain Specialist | ~2โ4 GB | Base ยท GGUF |
๐ฌ Lineup Highlights
- ๐ Viper-9B: The flagship for software engineering and complex reasoning. Demonstrates +14% absolute gain on LiveCodeBench v6, 84.7% on MBPP+, and calibrated factual honesty without confident hallucinations.
- ๐บ Cerberus-E4B: Efficient mid-weight specialist built on Google's Gemma 4 backbone, excelling in multi-turn tool interaction and structured bilingual reasoning.
- โก Mercury-1.7B: Sub-2B powerhouse powered by Liquid AI's hybrid linear attention and causal depthwise convolutions, delivering desktop-class reasoning at up to 200 tokens/sec on edge hardware.
- ๐ Mercury-Acad-1.7B: Tailored for mathematical research, paper comprehension, and STEM problem solving with dual-mode explicit reasoning (
<think>).
๐ฑ Client: rrchat
rrchat is a privacy-first mobile client designed to pair your phone directly with your PC or local server running llama.cpp, llama-server, or Ollama:
- ๐ 100% Local & Sovereign: Direct peer-to-peer connection over your local network/VPN. No middleman servers, no tracking, zero cloud lock-in.
- ๐๏ธ Full Multimodal Workflow: Integrated camera vision, audio voice notes transcription, and document analysis.
- ๐ Agentic Web Search: Privacy-preserving web exploration powered by local models without vendor profiling.
- โก Instant Pairing: One-tap connect via local IP / QR code with automatic model detection and context management.
Built by rrchat ยท Empowering sovereign open-source intelligence