---
tags:
  - gguf
  - tains
  - temple-nerve
base_model: JackFram/llama-68m
quantized_by: temple-forge
---

# Llama-68M — Q4_K_M GGUF

Quantized by the Temple AI Nervous System (TAINS) forge.

- **Base model**: [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m)
- **Parameters**: 68M
- **Quantization**: Q4_K_M
- **Neural tier**: spinal
- **File size**: 44.0MB

Converted using llama.cpp `convert_hf_to_gguf.py` + `llama-quantize`.