What are the hardware requirements for Trinity Nano Base?

Trinity Nano Base requires approximately 12.2 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Trinity Nano Base and how large is it?

Trinity Nano Base is developed by arcee-ai, a model with 6.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Trinity Nano Base?

Trinity Nano Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Trinity Nano Base by arcee-ai — VRAM 12.2GB, 128K context

Name: Trinity Nano Base
Author: arcee-ai

Trinity Nano Base is an open-source language model by arcee-ai. Features: 6.1b LLM, VRAM: 12.2GB, Context: 128K, License: other, LLM Explorer Score: 0.24.

Afmoe Ar Base model:arcee-ai/trinity-na... Base model:finetune:arcee-ai/t... Conversational Custom code De En Endpoints compatible Es Fr Hi It Ko Pt Region:us Ru Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/arcee-ai/Trinity-Nano-Base

Trinity Nano Base Parameters and Internals

LLM Name	Trinity Nano Base
Repository 🤗	https://huggingface.co/arcee-ai/Trinity-Nano-Base
Base Model(s)	Trinity Nano Base Pre Anneal arcee-ai/Trinity-Nano-Base-Pre-Anneal
Model Size	6.1b
Required VRAM	12.2 GB
Updated	2026-07-18
Maintainer	arcee-ai
Model Type	afmoe
Model Files	2.0 GB: 1-of-7 2.0 GB: 2-of-7 2.0 GB: 3-of-7 2.0 GB: 4-of-7 2.0 GB: 5-of-7 1.8 GB: 6-of-7 0.4 GB: 7-of-7
Supported Languages	en es fr de it pt ru ar hi ko zh
Model Architecture	AfmoeForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.57.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	200192

Rank the Trinity Nano Base capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Trinity Nano Base

Best Alternatives	Context / RAM	Downloads	Likes
Trinity Nano Preview	128K / 12.2 GB	18452	78
Dolphin X1 Trinity Nano	128K / 12.2 GB	151	30
Trinity Nano Preview FP8 Block	128K / 6.7 GB	325	1
Trinity Nano Base Pre Anneal	4K / 12.2 GB	66	14
Trinity Nano Preview MLX 8bit	128K / 6.4 GB	34	3

Note: green Score (e.g. "73.2") means that the model is better than arcee-ai/Trinity-Nano-Base.