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

Orion 14B LongChat by OrionStarAI

 »  All LLMs  »  OrionStarAI  »  Orion 14B LongChat   URL Share it on

  7   

Orion 14B LongChat is an open-source language model by OrionStarAI. Features: 14b LLM, VRAM: 29GB, Context: 195K, LLM Explorer Score: 0.12.

  Code   Custom code   En   Ja   Ko   Model   Orion   Pytorch   Region:us   Sharded   Zh
Model Card on HF 🤗: https://huggingface.co/OrionStarAI/Orion-14B-LongChat 

Orion 14B LongChat Benchmarks

LLME Score: 0.11743
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Orion 14B LongChat (OrionStarAI/Orion-14B-LongChat)
🌟 Advertise your project 🚀

Orion 14B LongChat Parameters and Internals

Model Type 
text generation, multilingual
Additional Notes 
Strong in multilingual chat scenarios with special attention to long-context tokens. Provides a variety of chat models including fine-tuned RAG and Plugin versions.
Supported Languages 
en (High), zh (High), ja (High), ko (High)
Training Details 
Data Sources:
2.5T multilingual corpus
Data Volume:
2.5 trillion tokens
Context Length:
320000
Hardware Used:
hundreds of GPUs
Input Output 
Input Format:
Prompts in JSON format with role and content.
Accepted Modalities:
text
Output Format:
Text responses
Performance Tips:
Utilize multiple GPUs for improved inference speed, a minimum of 4-bit integer weights for reduced model size.
Release Notes 
Version:
Orion-14B
Notes:
Initial release of the model with multiple variants including 4-bit quantized versions.
LLM NameOrion 14B LongChat
Repository 🤗https://huggingface.co/OrionStarAI/Orion-14B-LongChat 
Model Size14b
Required VRAM29 GB
Updated2026-03-11
MaintainerOrionStarAI
Model Typeorion
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   9.2 GB: 3-of-3
Supported Languagesen zh ja ko
Model ArchitectureOrionForCausalLM
Context Length200000
Model Max Length200000
Transformers Version4.34.0
Tokenizer ClassOrionTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size84608
Torch Data Typebfloat16

Quantized Models of the Orion 14B LongChat

Model
Likes
Downloads
VRAM
Orion 14B Chat67775329 GB

Best Alternatives to Orion 14B LongChat

Best Alternatives
Context / RAM
Downloads
Likes
Orion 14B LongChat 6.0bpw Exl195K / 11.5 GB12
Orion 14B Base Special4K / 29 GB751
Kor Resume Orion 14B4K / 29 GB290
Orion 14B Base4K / 29 GB40681
Orion 14B Chat RAG4K / 29 GB7832
Orion 14B Chat Int44K / 8.8 GB2328
Orion 14B Chat RAG Safetensors4K / 29 GB50
Orion 14B Chat Safetensors4K / 29 GB51
Orion 14B Base Int44K / 8.8 GB118
Orion 14B Chat Plugin4K / 29 GB238
Note: green Score (e.g. "73.2") means that the model is better than OrionStarAI/Orion-14B-LongChat.

Rank the Orion 14B LongChat 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