jenerallee78/Ministral-3-14B-abliterated
Quantization vs mistralai/Ministral-3-14B-Instruct-2512. mistralai/Ministral-3-14B-Instruct-2512 is a quantized version of the other (F8_E4M3/BF16).
4 derivatives checked
- mradermacher/Ministral-3-14B-abliterated-GGUF: Quantization (fewer layers)
- mradermacher/Ministral-3-14B-abliterated-i1-GGUF: Quantization (fewer layers)
- jenerallee78/Ministral-3-14B-abliterated-GGUF: Same weights, converted (fewer layers)
- SOMEHOTMEAL/Ministral-3-14B-Janus-Abliterated-V2-Base_And_GGUF: LoRA-style
2 other repos hold byte-for-byte identical weight files.