CoolFace
Modelpublic

matrixportalx/TR-V1-GGUF

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes14downloads
Model Card

TR-V1 GGUF Quantized Models

Technical Details

  • —Quantization Tool: llama.cpp
  • —Version: version: 5168 (ab47dec3)

Model Information

Available Files

🚀 Download🔢 Type📝 Description
DownloadQ4 K M4-bit balanced (recommended default)

💡 Q4 K M provides the best balance for most use cases