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

Loyal Piano M7 AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Loyal Piano M7 AWQ   URL Share it on

  5   

Loyal Piano M7 AWQ is an open-source language model by TheBloke. Features: 7.2b LLM, VRAM: 4.2GB, Context: 32K, License: cc-by-nc-4.0, Quantized, LLM Explorer Score: 0.11.

  4-bit   Awq Base model:chargoddard/loyal-p... Base model:quantized:chargodda...   Dataset:chargoddard/rpguild   Dataset:lemonilia/limarp Dataset:openai/summarize from ... Dataset:pankajmathur/orca mini...   Dataset:pygmalionai/pippa   En   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/loyal-piano-m7-AWQ 

Loyal Piano M7 AWQ Benchmarks

LLME Score: 0.10764
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Loyal Piano M7 AWQ (TheBloke/loyal-piano-m7-AWQ)
🌟 Advertise your project 🚀

Loyal Piano M7 AWQ Parameters and Internals

Model Type 
mistral
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
roleplay, long-context recall applications
Additional Notes 
Experimenting with dataset ratios for roleplay focus.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
pankajmathur/orca_mini_v1_dataset, openai/summarize_from_feedback, PygmalionAI/PIPPA, chargoddard/rpguild, lemonilia/LimaRP
Methodology:
AWQ quantization method, roleplay-focused model with some long-context recall abilities.
Context Length:
4096
Hardware Used:
Massed Compute
Input Output 
Input Format:
{prompt}
LLM NameLoyal Piano M7 AWQ
Repository 🤗https://huggingface.co/TheBloke/loyal-piano-m7-AWQ 
Model NameLoyal Piano M7
Model CreatorCharles Goddard
Base Model(s)  Loyal Piano M7   chargoddard/loyal-piano-m7
Model Size7.2b
Required VRAM4.2 GB
Updated2026-04-01
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Loyal Piano M7 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Functionary Small V2.4 AWQ32K / 4.2 GB41
Hc Mistral Alpaca Merged AWQ32K / 4.2 GB90
Garrulus AWQ32K / 4.2 GB42
Phoenix AWQ32K / 4.2 GB131
...ph Openchat 3.5 1210 Slerp AWQ32K / 4.2 GB32
Mistral Ft Optimized 1227 AWQ32K / 4.2 GB51
Metis 0.5 AWQ32K / 4.2 GB41
XDAN L1 Chat RL V1 AWQ32K / 4.2 GB31
Apricot Wildflower 20 AWQ32K / 4.2 GB41
OpenZephyrChat V0.2 AWQ32K / 4.2 GB83
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/loyal-piano-m7-AWQ.

Rank the Loyal Piano M7 AWQ 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? 52473 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