---
library_name: llama.cpp
tags:
- gguf
- llama3
- unsloth
- logscale
- humio
---

# LLM_FQL_LogScale (GGUF f16)

This repo contains a GGUF `f16` export for use with llama.cpp / Ollama / LM Studio.

## Files
- `model-f16.gguf`

## Notes
- This is an `f16` GGUF. For smaller sizes, quantize to `q4_k_m` using llama.cpp `quantize`.