Apps & Tools
Neon Nova
High-performance EXL3 quantizations of Hy4-flash for the TandemLLM engine.
by0xBakeer
Is this your creation?
Playable
Description
A collection of specialized EXL3 quantizations for Tencent's Hy4-flash and Qwen3.8-Flash-Next models, optimized for the TandemLLM engine on DGX hardware. The suite provides high-fidelity weights at 3.56 and 3.08 bits per weight alongside coding examples for multimodal outputs including videos and diagrams.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.