What are the hardware requirements for EdiTikZ 4B?

EdiTikZ 4B requires approximately 9.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed EdiTikZ 4B and how large is it?

EdiTikZ 4B is developed by nllg, a model with 4b 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 EdiTikZ 4B?

EdiTikZ 4B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

EdiTikZ 4B by nllg — VRAM 9.1GB

Name: EdiTikZ 4B
Author: nllg

EdiTikZ 4B is an open-source language model by nllg. Features: 4b LLM, VRAM: 9.1GB, License: apache-2.0, LLM Explorer Score: 0.28.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-4b Code-generation Conversational Image-editing Image-text-to-text Latex Multimodal Qwen3 5 Region:us Safetensors Scientific-figures Tikz

Model Card on HF 🤗: https://huggingface.co/nllg/EdiTikZ-4B

EdiTikZ 4B Parameters and Internals

LLM Name	EdiTikZ 4B
Repository 🤗	https://huggingface.co/nllg/EdiTikZ-4B
Base Model(s)	Qwen/Qwen3.5-4B Qwen/Qwen3.5-4B
Model Size	4b
Required VRAM	9.1 GB
Updated	2026-09-11
Maintainer	nllg
Model Type	qwen3_5
Model Files	9.1 GB
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.3.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the EdiTikZ 4B 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 EdiTikZ 4B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 4B	0K / 9.3 GB	6575502	801
NuExtract3	0K / 0.2 GB	441570	324
Agents A1 4B	0K / 9.1 GB	177578	72
CogEvol 4B	0K / 9.1 GB	743	25
Qwen3.5 4B Base	0K / 9.3 GB	227814	79
Qwen3.8 4B Distill	0K / 9.3 GB	1878	26
Fara1.5 4B	0K / 9.1 GB	4934	39
Qwen3.5 4B	0K / 9.3 GB	139961	26
Qwen35 4b Sft VE	0K / 9.1 GB	3663	0
DeepSeek V4 Pro Qwen3.5 4B	0K / 9.3 GB	3476	9

Note: green Score (e.g. "73.2") means that the model is better than nllg/EdiTikZ-4B.