Forgotten Safeword 12B V4.0 is an open-source language model by ReadyArt. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, LLM Explorer Score: 0.2.
Base model:finetune:thedrummer... Base model:thedrummer/unslopne... Dangerous En Erp Explicit Mistral Nsfw Region:us Roleplay Safetensors Sharded Tensorflow Unaligned
Model Card on HF 🤗: https://huggingface.co/ReadyArt/Forgotten-Safeword-12B-v4.0
Forgotten Safeword 12B V4.0 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Forgotten Safeword 12B V4.0 Parameters and Internals
| LLM Name | Forgotten Safeword 12B V4.0 |
| Repository 🤗 | https://huggingface.co/ReadyArt/Forgotten-Safeword-12B-v4.0 |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-10-13 |
| Maintainer | ReadyArt |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Forgotten Safeword 12B V4.0
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Celestial Queen 12B | 1000K / 24.5 GB | 305 | 8 |
| Celestial Queen 12B Heretic | 1000K / 24.5 GB | 33 | 3 |
| MN 12B Mag Mell R1 | 1000K / 24.5 GB | 1458 | 236 |
| Captain Eris Violet V0.420 12B | 1000K / 24.5 GB | 2003 | 54 |
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 2844 | 138 |
| ...s PersonalityEngine V1.1.0 12B | 1000K / 24.5 GB | 651 | 45 |
| Captain Eris BMO Violent 12B | 1000K / 24.5 GB | 305 | 2 |
| Dans SakuraKaze V1.0.0 12B | 1000K / 24.5 GB | 11 | 20 |
| Impish Nemo 12B | 1000K / 24.5 GB | 2078 | 70 |
| ...n Eris BMO Violent GRPO V0.420 | 1000K / 24.5 GB | 92 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than ReadyArt/Forgotten-Safeword-12B-v4.0 .
Rank the Forgotten Safeword 12B V4.0 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a