Available Models

Mistral-Nemo-12B-R1-v0.1-Q4_K_M-GGUF

Model Information

  • Format: GGUF (4-bit quantized)
  • Size: ~12B parameters
  • Base Model: Mistral-Nemo
  • Quantization: Q4_K_M

Installation

from transformers import AutoModel
model = AutoModel.from_pretrained("CreitinGameplays/Mistral-Nemo-12B-R1-v0.1-Q4_K_M-GGUF", dtype="auto")

Requirements

• Minimum 16GB RAM

• 8GB+ VRAM for GPU acceleration

• Transformers library installed