ollama run hf.co/el4/GRM-3.2-Sky-ONYX-GGUF:GRM-3.2-Sky-ONYX-mini.gguf
To prove this extreme compression didn't lobotomize the model, we subjected the ~11GB ONYX-mini quant to a grueling 20-minute agentic stress test designed to break long-horizon reasoning. We tasked the model with writing a compilable Rust program to calculate quantum harmonic oscillator eigenvalues via
nalgebramatrix diagonalization, forcing it to execute the code viabash, read the compiler errors, and autonomously debug its own Unicode and eigenvalue-sorting bugs. After successfully patching the math to achieve <0.05% analytical error, the model seamlessly passed the entire technical explanation through a three-step translation gauntlet into formal Japanese, Spanish, and colloquial Egyptian Arabic. The fact that a heavily crushed 35B MoE running on a consumer laptop GPU can hold the working memory required to write physics code, runcargo build, fix its own mistakes, and perfectly execute multilingual code-switching in just 20 minutes proves that ONYX doesn't just shrink the weights—it preserves the model's agentic soul.
recommended sampling parameters:
--temp 0.85 --top-p 0.95 --top-k 40 --min-p 0.05 --repeat-penalty 1.1 --presence-penalty 0.0