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

Metharme 13B 4bit GPTQ by TehVenom

 »  All LLMs  »  TehVenom  »  Metharme 13B 4bit GPTQ   URL Share it on

  7   

Metharme 13B 4bit GPTQ is an open-source language model by TehVenom. Features: 13b LLM, VRAM: 7.5GB, Context: 2K, Quantized, Instruction-Based, LLM Explorer Score: 0.07.

  4bit   En   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TehVenom/Metharme-13b-4bit-GPTQ 

Metharme 13B 4bit GPTQ Benchmarks

LLME Score: 0.07488
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Metharme 13B 4bit GPTQ (TehVenom/Metharme-13b-4bit-GPTQ)
🌟 Advertise your project 🚀

Metharme 13B 4bit GPTQ Parameters and Internals

Model Type 
text generation, instruct
Use Cases 
Primary Use Cases:
Fictional writing, Entertainment purposes
Limitations:
Not fine-tuned to be safe and harmless, May contain profanity or offensive text, Outputs might often be factually wrong or misleading
Additional Notes 
The model always starts by generating a BOS token. This is an accidental side-effect which is planned to be addressed in future versions.
Training Details 
Methodology:
Supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories and conversations with synthetically generated instructions attached. Trained as a LoRA, then merged down to the base model.
Input Output 
Input Format:
Uses <|system|>, <|user|>, and <|model|> tokens for conversation history.
Accepted Modalities:
text
Output Format:
Generates formatted text responses based on prompts
Performance Tips:
Best to do a sliding window over the user and model turns, but keep the system prompt fixed at the start of the context window.
LLM NameMetharme 13B 4bit GPTQ
Repository 🤗https://huggingface.co/TehVenom/Metharme-13b-4bit-GPTQ 
Model Size13b
Required VRAM7.5 GB
Updated2026-03-09
MaintainerTehVenom
Model Typellama
Instruction-BasedYes
Model Files  7.5 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.29.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Metharme 13B 4bit GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven 13B GPTQ16K / 7.3 GB137
CodeLlama 13B Instruct GPTQ16K / 7.3 GB15139
...sianai 13B Chat Bilingual GPTQ8K / 7.3 GB114
Leo Hessianai 13B Chat GPTQ8K / 7.3 GB121
...lama2 13B Orca V2 8K 3166 GPTQ8K / 7.3 GB924
Swallow 13B Instruct GPTQ4K / 7.5 GB82
Mythalion 13B GPTQ4K / 7.3 GB9452
Pygmalion 2 13B GPTQ4K / 7.3 GB1241
...2 13B Ft Instruct Es Gptq 3bit4K / 5.7 GB63
Speechless Llama2 13B GPTQ4K / 7.3 GB92
Note: green Score (e.g. "73.2") means that the model is better than TehVenom/Metharme-13b-4bit-GPTQ.

Rank the Metharme 13B 4bit GPTQ 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? 52509 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