Litter

All projects

Apps & Tools

A high-performance cat-themed interface for high-speed local LLM inference.

by0xSero

PlayableOpen source

Litter media is blocked

Allow external media to connect to the provider and play this content.

Description

A specialized local chat interface designed to handle extreme token generation speeds, demonstrating performance up to 240 tokens per second. The UI features a cat-themed design language and focuses on maximizing throughput and responsiveness for advanced models like GLM-5.3-Flash.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: Demonstrates impressive capability by achieving extremely high-speed local inference (240 tok/s) within a custom UI.
Attributed to: @0xsero
Built with: Gemini 3.8 Flash TTS V4.1 Flash 3.8 Flash Gemini 3.8 Flash Cyber Omni 1.1 Flash Ling 3.0 Flash Fin GLM-5.3-Flash Ox Alpha GLM-5.3 Gemini 3.7 Flash Qwen3.7 Flash 3.5 Flash Cyber 3.6 Flash Step 3.7 Flash Gemini 3.5 Flash 2.5 Flash
Links: localstudio.ai
View tweet
View GitHub repo
Tags: #local-llm #chat-ui #performance

Discovered: X
First posted: X · Sep 25, 2026
Listed: Added 6h ago
Build: Moderate
Models: Strong

Litter

Description

Timeline

Litter

Description

Timeline