Kaolinite Kitara 12B is an open-source language model by XCryptoniusX. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, Merged, LLM Explorer Score: 0.18.
Merged Model Chatml Conversational Creative-writing Endpoints compatible English Mistral Region:us Roleplay Safetensors Sharded Storytelling Tensorflow
Model Card on HF 🤗: https://huggingface.co/XCryptoniusX/Kaolinite-Kitara-12B
Kaolinite Kitara 12B 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)
Kaolinite Kitara 12B Parameters and Internals
| LLM Name | Kaolinite Kitara 12B |
| Repository 🤗 | https://huggingface.co/XCryptoniusX/Kaolinite-Kitara-12B |
| Merged Model | Yes |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2026-05-22 |
| Maintainer | XCryptoniusX |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.51.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 131078 |
| Torch Data Type | bfloat16 |
Best Alternatives to Kaolinite Kitara 12B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MN 12B Mag Mell R1 | 1000K / 24.5 GB | 69558 | 238 |
| Qliphoth 12B V1.2 | 1000K / 24.5 GB | 54 | 2 |
| Qliphoth 12B V1 | 1000K / 24.5 GB | 141 | 1 |
| Qliphoth 12B V1.1 | 1000K / 24.5 GB | 112 | 1 |
| MN 12B LucidFaun RP RU | 1000K / 24.5 GB | 191 | 5 |
| Celestial Queen 12B | 1000K / 24.5 GB | 39 | 12 |
| Captain Eris BMO Violent 12B | 1000K / 24.5 GB | 305 | 2 |
| Tankie DPE 12B SFT V2 | 1000K / 24.5 GB | 412 | 7 |
| Dans SakuraKaze V1.0.0 12B | 1000K / 24.5 GB | 47 | 20 |
| SauerkrautLM Nemo 12B Instruct | 1000K / 24.5 GB | 9812 | 22 |
Note: green Score (e.g. "73.2") means that the model is better than XCryptoniusX/Kaolinite-Kitara-12B .
Rank the Kaolinite Kitara 12B 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? 54253 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