What are the hardware requirements for NV Reason CXR 3B?

NV Reason CXR 3B requires approximately 8.1 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed NV Reason CXR 3B and how large is it?

NV Reason CXR 3B is developed by nvidia, a model with 3b 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 NV Reason CXR 3B?

NV Reason CXR 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

NV Reason CXR 3B by nvidia — VRAM 8.1GB, 125K context

Name: NV Reason CXR 3B
Author: nvidia

NV Reason CXR 3B is an open-source language model by nvidia. Features: 3b LLM, VRAM: 8.1GB, Context: 125K, License: other, Instruction-Based, LLM Explorer Score: 0.23.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-3b-... Conversational Cxr En Endpoints compatible Image-text-to-text Instruct Nvidia Qwen2 5 vl Region:us Safetensors Sharded Tensorflow X-ray

Model Card on HF 🤗: https://huggingface.co/nvidia/NV-Reason-CXR-3B

NV Reason CXR 3B Parameters and Internals

LLM Name	NV Reason CXR 3B
Repository 🤗	https://huggingface.co/nvidia/NV-Reason-CXR-3B
Base Model(s)	Qwen/Qwen2.5-VL-3B-Instruct Qwen/Qwen2.5-VL-3B-Instruct
Model Size	3b
Required VRAM	8.1 GB
Updated	2026-08-10
Maintainer	nvidia
Model Type	qwen2_5_vl
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 3.1 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen2_5_VLForConditionalGeneration
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	4.56.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the NV Reason CXR 3B 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 NV Reason CXR 3B

Best Alternatives	Context / RAM	Downloads	Likes
Nanonets OCR2 3B	125K / 7.5 GB	659329	511
Qwen2.5 VL 3B Instruct	125K / 7.5 GB	7336490	683
Nanonets OCR S	125K / 7.5 GB	52151	1591
Typhoon Ocr 3B	125K / 7.5 GB	356913	9
Spatial SSRL 3B	125K / 8.2 GB	161	7
CapRL 3B	125K / 7.5 GB	230	47
ScaleCUA 3B	125K / 7.5 GB	261	13
CapRL Eval 3B	125K / 7.5 GB	87	8
Nanonets OCR S Bf16	125K / 7.5 GB	96	2
Qwen2.5 VL 3B Instruct	125K / 7.5 GB	2710	6

Note: green Score (e.g. "73.2") means that the model is better than nvidia/NV-Reason-CXR-3B.