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

Trinity Large Preview by arcee-ai

 »  All LLMs  »  arcee-ai  »  Trinity Large Preview   URL Share it on

  992   

Trinity Large Preview is an open-source language model by arcee-ai. Features: 398.6b LLM, VRAM: 798.4GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.37.

  Arxiv:2602.17004   Afmoe   Ar Base model:arcee-ai/trinity-la... Base model:finetune:arcee-ai/t...   Conversational   Custom code   De   En   Endpoints compatible   Es   Eval-results   Fr   Hi   It   Ko   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/arcee-ai/Trinity-Large-Preview 

Trinity Large Preview Benchmarks

LLME Score: 0.36652
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Trinity Large Preview (arcee-ai/Trinity-Large-Preview)
🌟 Advertise your project 🚀

Trinity Large Preview Parameters and Internals

LLM NameTrinity Large Preview
Repository 🤗https://huggingface.co/arcee-ai/Trinity-Large-Preview 
Base Model(s)  arcee-ai/Trinity-Large-Base   arcee-ai/Trinity-Large-Base
Model Size398.6b
Required VRAM798.4 GB
Updated2026-03-27
Maintainerarcee-ai
Model Typeafmoe
Model Files  2.5 GB: 1-of-31   0.7 GB: 2-of-31   0.7 GB: 3-of-31   0.7 GB: 4-of-31   29.4 GB: 5-of-31   29.4 GB: 6-of-31   29.4 GB: 7-of-31   29.4 GB: 8-of-31   29.4 GB: 9-of-31   29.4 GB: 10-of-31   29.4 GB: 11-of-31   29.4 GB: 12-of-31   29.4 GB: 13-of-31   29.4 GB: 14-of-31   29.4 GB: 15-of-31   29.4 GB: 16-of-31   29.4 GB: 17-of-31   29.4 GB: 18-of-31   29.4 GB: 19-of-31   29.4 GB: 20-of-31   29.4 GB: 21-of-31   29.4 GB: 22-of-31   29.4 GB: 23-of-31   29.4 GB: 24-of-31   29.4 GB: 25-of-31   29.4 GB: 26-of-31   29.4 GB: 27-of-31   29.4 GB: 28-of-31   29.4 GB: 29-of-31   29.4 GB: 30-of-31   29.4 GB: 31-of-31
Supported Languagesen es fr de it pt ru ar hi ko zh
Model ArchitectureAfmoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size200192

Rank the Trinity Large Preview 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? 52052 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 v20260327b
  Support LLM Explorer