What are the hardware requirements for Karti Small VL 4B NVFP4?

Karti Small VL 4B NVFP4 requires approximately 4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Karti Small VL 4B NVFP4 and how large is it?

Karti Small VL 4B NVFP4 is developed by KartiOS, 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 Karti Small VL 4B NVFP4?

Karti Small VL 4B NVFP4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Karti Small VL 4B NVFP4 by KartiOS — VRAM 4GB

Name: Karti Small VL 4B NVFP4
Author: KartiOS

Karti Small VL 4B NVFP4 is an open-source language model by KartiOS. Features: 4b LLM, VRAM: 4GB, License: apache-2.0, LLM Explorer Score: 0.29.

8-bit Base model:kartios/karti-small... Base model:quantized:kartios/k... Blackwell Compressed-tensors Conversational Endpoints compatible Image-text-to-text Nvfp4 Quantized Qwen3 5 Region:us Safetensors Tool-calling Vision Vision-language

Model Card on HF 🤗: https://huggingface.co/KartiOS/Karti-Small-VL-4B-NVFP4

Karti Small VL 4B NVFP4 Parameters and Internals

LLM Name	Karti Small VL 4B NVFP4
Repository 🤗	https://huggingface.co/KartiOS/Karti-Small-VL-4B-NVFP4
Base Model(s)	Karti Small VL 4B KartiOS/Karti-Small-VL-4B
Model Size	4b
Required VRAM	4 GB
Updated	2026-09-02
Maintainer	KartiOS
Model Type	qwen3_5
Model Files	4.0 GB
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.14.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Karti Small VL 4B NVFP4 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 Karti Small VL 4B NVFP4

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
Qwen3.8 4B Distill	0K / 9.3 GB	1878	26
Qwen3.5 4B Base	0K / 9.3 GB	227814	79
Fara1.5 4B	0K / 9.1 GB	4934	39
CogEvol 4B	0K / 9.1 GB	1	18
Qwen3.5 4B	0K / 9.3 GB	139961	26
ASL 4B V1	0K / 9.3 GB	119	11
Qwen35 4b Sft VE	0K / 9.1 GB	3663	0

Note: green Score (e.g. "73.2") means that the model is better than KartiOS/Karti-Small-VL-4B-NVFP4.