ProCreations/Ternary-Bonsai-2-27B-DFlash2
Not comparable yet vs prism-ml/Ternary-Bonsai-2-27B-gguf. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (28 of 851/81 match), usually an architecture llama.cpp's name map doesn't cover yet.
2 derivatives checked
- zenlm/zen6-flash: Quantization
- zerodegress/Ternary-Bonsai-2-27B-DFlash2-mlx-4bit: Quantization