JLatter/

Qwen3.6-35B-A3B-PrismScout-4.85bit

Mixed-precision quantization of Qwen/Qwen3.6-35B-A3B produced by PrismaScout — a per-Linear sensitivity-driven allocator that chooses each Linear module's format individually under a total-bit budget.

All credit for PrismScout goes out to Rob Tand! Links Source: github.com/RobTand/prismaquant Base model: Qwen/Qwen3.6-35B-A3B

Citation @software{prismaquant2026, title = {PrismaQuant: per-Linear sensitivity-driven mixed-precision quantization for LLMs}, author = {Tand, Rob}, year = 2026, url = {https://github.com/RobTand/prismaquant}, }