PsychoPomp 20B by Elfrino

 »  All LLMs  »  Elfrino  »  PsychoPomp 20B   URL Share it on

PsychoPomp 20B is an open-source language model by Elfrino. Features: 20b LLM, VRAM: 40GB, Context: 4K, Merged, LLM Explorer Score: 0.15.

  Merged Model Base model:elfrino/xwinxtended... Base model:undi95/mxlewd-l2-20...   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

PsychoPomp 20B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

PsychoPomp 20B Parameters and Internals

LLM NamePsychoPomp 20B
Repository 🤗https://huggingface.co/Elfrino/PsychoPomp-20B 
Base Model(s)  XwinXtended 20B   MXLewd L2 20B   Elfrino/XwinXtended-20B   Undi95/MXLewd-L2-20B
Merged ModelYes
Model Size20b
Required VRAM40 GB
Updated2026-04-26
MaintainerElfrino
Model Typellama
Model Files  5.0 GB: 1-of-9   5.0 GB: 2-of-9   4.9 GB: 3-of-9   4.9 GB: 4-of-9   4.9 GB: 5-of-9   5.0 GB: 6-of-9   5.0 GB: 7-of-9   4.9 GB: 8-of-9   0.4 GB: 9-of-9
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.33.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to PsychoPomp 20B

Best Alternatives
Context / RAM
Downloads
Likes
Internlm2 5 20B Llamafied256K / 39.9 GB16585
Stellaris Internlm2 20B R51232K / 39.8 GB93
Internlm2 Chat 20B Llama Old32K / 39.6 GB623
Internlm2 Base 20B Llama32K / 39.6 GB73
Internlm2 Base 20B Llama32K / 39.6 GB60
Internlm2 20B Llama32K / 39.6 GB20020
Deita 20B32K / 39.8 GB631
Bagel 20B V04 Llama32K / 39.6 GB107
Bagel DPO 20B V04 Llama32K / 39.6 GB183
Internlm2 Limarp Chat 20B32K / 39.6 GB113
Note: green Score (e.g. "73.2") means that the model is better than Elfrino/PsychoPomp-20B.

Rank the PsychoPomp 20B 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? 53972 in total.

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