What are the hardware requirements for Rakedoc Nano 2?

Rakedoc Nano 2 requires approximately 2.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Rakedoc Nano 2 and how large is it?

Rakedoc Nano 2 is developed by cloudraker, a model with 1.2b 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 Rakedoc Nano 2?

Rakedoc Nano 2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Rakedoc Nano 2 by cloudraker — VRAM 2.3GB

Name: Rakedoc Nano 2
Author: cloudraker

Rakedoc Nano 2 is an open-source language model by cloudraker. Features: 1.2b LLM, VRAM: 2.3GB, License: agpl-3.0, LLM Explorer Score: 0.34.

Base model:finetune:kdlai/kdl-... Base model:kdlai/kdl-frontier-... Chart-extraction Conversational Document-parsing Endpoints compatible Image-text-to-text Ocr Parsebench Qwen2 vl Region:us Safetensors Table-extraction

Model Card on HF 🤗: https://huggingface.co/cloudraker/rakedoc-nano-2

Rakedoc Nano 2 Parameters and Internals

LLM Name	Rakedoc Nano 2
Repository 🤗	https://huggingface.co/cloudraker/rakedoc-nano-2
Base Model(s)	KDL Frontier Parser Nano V2 KDLAI/KDL-Frontier-Parser-nano-v2
Model Size	1.2b
Required VRAM	2.3 GB
Updated	2026-11-11
Maintainer	cloudraker
Model Type	qwen2_vl
Model Files	2.3 GB
Model Architecture	Qwen2VLForConditionalGeneration
License	agpl-3.0
Model Max Length	16384
Transformers Version	5.22.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Rakedoc Nano 2 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 Rakedoc Nano 2

Best Alternatives	Context / RAM	Downloads	Likes
MinerU2.5 Pro 2604 1.2B	32K / 2.3 GB	250130	164
MinerU2.5 Pro 2605 1.2B	32K / 2.3 GB	56590	56
Cae	16K / 2.3 GB	26	1
KDL Frontier Parser Nano	0K / 2.3 GB	6632	19
Rakedoc Nano	0K / 2.3 GB	244	4
Florin Parser Nano	0K / 2.3 GB	24	1
...nerU2.5 Pro 2605 1.2B Mlx 4bit	32K / 1.7 GB	50	1

Note: green Score (e.g. "73.2") means that the model is better than cloudraker/rakedoc-nano-2.