DavidAU/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC
LoRA-style vs mistralai/Mistral-Nemo-Instruct-2407. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 0/1
10 derivatives checked
- mradermacher/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-GGUF: Quantization
- mradermacher/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-i1-GGUF: Quantization
- nightmedia/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-qx86-hi-mlx: Quantization
- Medvedko/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-Q4_K_M-GGUF: Quantization
- fairy322/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-GGUF: Quantization
- RicardoEstep/RPBizkit-v11-12B-Thinking: Full fine-tune
- pinkachu/Menage-12B: Full fine-tune
- kryp1234/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-GGUF: Quantization
- liodon-ai/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-FP8: Quantization
- Chuncho32/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-Q8_0-GGUF: Quantization
6 other repos hold byte-for-byte identical weight files.