Description

A performance-tuned inference engine featuring EXL3 quantization (5.75 bpw) and MTP speculative decoding. It is optimized for the NVIDIA RTX 5090, achieving throughput over 148 tok/s and successfully powering complex agentic tasks like one-shot 3D scene generation.

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