GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

maczzzzzz author hub

Grug 12B TQ3 4S — GGUF TQ3 4S quant of kai os/Grug 12B — a compact reasoning fine tune of google/gemma 4 12B it, produced via turbo tan's llama.cpp tq3 CUDA fork. Benchmarked on a Blackwell RTX 5060 Ti 16 GB . Context scaling is comfortable: 152k at q4 0 KV with ~55 t/s throughp…

Models
12
Downloads
3,851

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models