GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

piskle author hub

Microsoft's Phi 4 14B, but heavily simplified. This model's raw weights were converted to GGUF compliant IQ2 XXS, ensuring some kind of stability with the heaviest compression possible. For smooth inference, it is recommended to have at least of 16GB of RAM or a GPU with 6GB of …

Models
2
Downloads
1

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