Orion 14B Base Int4 is an open-source language model by OrionStarAI. Features: 14b LLM, VRAM: 8.8GB, Context: 4K, LLM Explorer Score: 0.12.
Model Card on HF 🤗: https://huggingface.co/OrionStarAI/Orion-14B-Base-Int4
Orion 14B Base Int4 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Orion 14B Base Int4 Parameters and Internals
| Model Type |
| ||||||
| Additional Notes |
| ||||||
| Training Details |
|
| LLM Name | Orion 14B Base Int4 |
| Repository 🤗 | https://huggingface.co/OrionStarAI/Orion-14B-Base-Int4 |
| Model Size | 14b |
| Required VRAM | 8.8 GB |
| Updated | 2026-04-01 |
| Maintainer | OrionStarAI |
| Model Type | orion |
| Model Files | |
| Supported Languages | en zh ja ko |
| Model Architecture | OrionForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | OrionTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 84608 |
| Torch Data Type | float16 |
Best Alternatives to Orion 14B Base Int4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Orion 14B LongChat | 195K / 29 GB | 7 | 25 |
| Orion 14B LongChat 6.0bpw Exl | 195K / 11.5 GB | 1 | 2 |
| Orion 14B Base Special | 4K / 29 GB | 75 | 1 |
| Kor Resume Orion 14B | 4K / 29 GB | 29 | 0 |
| Orion 14B Base | 4K / 29 GB | 406 | 81 |
| Orion 14B Chat RAG | 4K / 29 GB | 78 | 32 |
| Orion 14B Chat Int4 | 4K / 8.8 GB | 23 | 28 |
| Orion 14B Chat RAG Safetensors | 4K / 29 GB | 5 | 0 |
| Orion 14B Chat Safetensors | 4K / 29 GB | 5 | 1 |
| Orion 14B Chat Plugin | 4K / 29 GB | 23 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than OrionStarAI/Orion-14B-Base-Int4 .
Rank the Orion 14B Base Int4 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! 🌟
What open-source LLMs or SLMs are you in search of? 52473 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a