LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Pantheon RP Pure 1.6.2 22B Small by Gryphe

 »  All LLMs  »  Gryphe  »  Pantheon RP Pure 1.6.2 22B Small   URL Share it on

  14   

Pantheon RP Pure 1.6.2 22B Small is an open-source language model by Gryphe. Features: 22b LLM, VRAM: 44.7GB, Context: 128K, License: other, Instruction-Based, LLM Explorer Score: 0.24.

  Axolotl Base model:finetune:mistralai/... Base model:mistralai/mistral-s...   Chatml   En   Finetuned   Instruct   Mistral   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small 

Pantheon RP Pure 1.6.2 22B Small Benchmarks

MMLU Pro: 32.69
GPQA: 10.51
MUSR: 4.39
BBH: 31.68
IFEval: 69.31 vs 88 (so35)-21.2%
MATH Lvl 5: 20.24
LLME Score: 0.24029
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pantheon RP Pure 1.6.2 22B Small (Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small)
🌟 Advertise your project 🚀

Pantheon RP Pure 1.6.2 22B Small Parameters and Internals

Model Type 
roleplay, story writing
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
roleplay, story writing
Additional Notes 
Pantheon is designed for a diverse roleplay experience with simple activation phrases for different personas. It is capable of handling both roleplay and story writing.
Supported Languages 
en (Full Proficiency)
Training Details 
Data Sources:
SlimOrca Sonnet dataset, Sonnet 3.5 Pantheon-styled generic roleplay dataset, Sonnet 3.5 Pantheon Persona dataset, Lyra the Assistant
Methodology:
Instruct-tuned flavour with a multi-stage strategy alteration due to base model specifics
Input Output 
Input Format:
[INST] System Prompt [Stimulus][/INST] Response
Output Format:
Textual dialogue
LLM NamePantheon RP Pure 1.6.2 22B Small
Repository 🤗https://huggingface.co/Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small 
Base Model(s)  Mistral Small Instruct 2409   mistralai/Mistral-Small-Instruct-2409
Model Size22b
Required VRAM44.7 GB
Updated2026-04-19
MaintainerGryphe
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   4.9 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   4.9 GB: 7-of-9   5.0 GB: 8-of-9   5.0 GB: 9-of-9
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token[control_748]
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Pantheon RP Pure 1.6.2 22B Small

Best Alternatives
Context / RAM
Downloads
Likes
MS Schisandra 22B V0.2128K / 44.7 GB179
MS Meadowlark 22B128K / 44.7 GB1116
MS Inky 2409 22B128K / 44.7 GB60
MS Quadrosiac 2409 22B128K / 44.7 GB90
MS Fujin 2409 22B128K / 44.7 GB80
... V4x1.6.2RP Cydonia VXXX 22B 8128K / 44.7 GB55
MS Dampf 2409 22B128K / 44.7 GB70
MS Physician 2409 22B128K / 44.7 GB70
Beeper King 22B128K / 44.7 GB97
MS A Coolyte 2409 22B128K / 44.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small.

Rank the Pantheon RP Pure 1.6.2 22B Small 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53254 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer