LLMRepos·On-Device / Small Models LLM projects

14MB foundation model for tiny devices; phones, wearables, smart home, and robots.

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt

The collection of pre-trained, state-of-the-art AI models for ailia SDK

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Soprano: Instant, Ultra-Realistic Text-to-Speech

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

Interface for OuteTTS models.

Pretrained model hub for Keras 3.

GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters

Rust bindings to https://github.com/k2-fsa/sherpa-onnx

电子鹦鹉 / Toy Language Model

A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题

Local Qwen 3.8 27B uncensored Q4_K_M + harvested SYSTEM pack. Official 3.8 weights, not a 3.6 retitle.