Merged Model Autotrain compatible Base model:epiculous/violet tw... Base model:marinaraspaghetti/n... Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/DoppelReflEx/MN-12B-Unleashed-Twilight
MN 12B Unleashed Twilight Benchmarks
MMLU Pro: 29.75
GPQA: 10.51
MUSR: 14.5
BBH: 35.98
IFEval: 35.05 vs 88 (so35)-60.2%
MATH Lvl 5: 9.59
LLME Score: 0.29069
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)
MN 12B Unleashed Twilight Parameters and Internals
| LLM Name | MN 12B Unleashed Twilight |
| Repository 🤗 | https://huggingface.co/DoppelReflEx/MN-12B-Unleashed-Twilight |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-06-09 |
| Maintainer | DoppelReflEx |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to MN 12B Unleashed Twilight
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 604025 | 119 |
| Captain Eris Violet V0.420 12B | 1000K / 24.5 GB | 5202 | 47 |
| MN 12B Mag Mell R1 | 1000K / 24.5 GB | 13242 | 170 |
| PLLuM 12B Nc Chat | 1000K / 24.5 GB | 6718 | 6 |
| Captain Eris BMO Violent 12B | 1000K / 24.5 GB | 305 | 2 |
| ...s PersonalityEngine V1.1.0 12B | 1000K / 24.5 GB | 438 | 40 |
| Dans SakuraKaze V1.0.0 12B | 1000K / 24.5 GB | 48 | 19 |
| MISCHIEVOUS 12B Mix III Ex V | 1000K / 24.5 GB | 1604 | 0 |
| ...n Eris BMO Violent GRPO V0.420 | 1000K / 24.5 GB | 92 | 3 |
| Magnum V2 12B | 1000K / 24.5 GB | 18683 | 89 |
Note: green Score (e.g. "73.2") means that the model is better than DoppelReflEx/MN-12B-Unleashed-Twilight .
Rank the MN 12B Unleashed Twilight 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? 48023 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124