What are the hardware requirements for Dart V2 Base?

Dart V2 Base requires approximately 0.2 GB of VRAM and supports a context window of 1K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Dart V2 Base and how large is it?

Dart V2 Base is developed by p1atdev, a model with 100m 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 Dart V2 Base?

Dart V2 Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Dart V2 Base by p1atdev — VRAM 0.2GB, 1K context

Name: Dart V2 Base
Author: p1atdev

Dart V2 Base is an open-source language model by p1atdev. Features: 100m LLM, VRAM: 0.2GB, Context: 1K, License: apache-2.0, LLM Explorer Score: 0.12.

Danbooru Dataset:isek-ai/danbooru-tags-... Mistral Onnx Optimum Region:us Safetensors Sft Trl

Model Card on HF 🤗: https://huggingface.co/p1atdev/dart-v2-base

Dart V2 Base Parameters and Internals

Model Type

Causal language model

Additional Notes

Evaluation has not been done yet and it needs to evaluate.

Training Details

Data Sources:

isek-ai/danbooru-tags-2024

Data Volume:

7M size of danbooru tags dataset since 2005 to 2024/03/31

Hardware Used:

8x RTX A6000

Model Architecture:

Mistral

Input Output

Input Format:

<|bos|> ...

Accepted Modalities:

text

Output Format:

tags format

LLM Name	Dart V2 Base
Repository 🤗	https://huggingface.co/p1atdev/dart-v2-base
Model Size	100m
Required VRAM	0.2 GB
Updated	2026-07-26
Maintainer	p1atdev
Model Type	mistral
Model Files	0.2 GB
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	1024
Model Max Length	1024
Transformers Version	4.38.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	30649
Torch Data Type	bfloat16

Rank the Dart V2 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 Dart V2 Base

Best Alternatives	Context / RAM	Downloads	Likes
Endurance 100B V1.1	128K / 200.2 GB	4	3
Endurance 100B V1	128K / 200.1 GB	2	12
Lazarus 2407 100B	128K / 200.2 GB	5	9
Mistral 100M Textbooks	32K / 0.5 GB	111	3
Dart V2 Sft	1K / 0.2 GB	2474	2

Note: green Score (e.g. "73.2") means that the model is better than p1atdev/dart-v2-base.