🧠
Typhoon Ocr 3b model by Typhoon Ai
⭐ 55.7
🧠
Model

Typhoon Ocr 3b

by Typhoon Ai typhoon-ai/typhoon-ocr-3b
Free2AITools Nexus Index
55.7
S: Semantic 50

Query-time baseline · scored live at search

A: Authority 44
P: Popularity 39
R: Recency 100
Q: Quality 65
Tech Context
3.75 Params
32.768K Ctx
Vital Performance
4.9K DL / 30D
Source β†’
Low FNI signal 55.7 FNI Score
3.75B Params
32k Context
4.9K Downloads
8G GPU ~6GB Est. VRAM
Dense QWEN2_5_VLFORCONDITIONALGENERATION Architecture
Commercial APACHE License
Model Information Summary
Entity Passport
Registry ID typhoon-ai/typhoon-ocr-3b
License Apache-2.0
Provider huggingface
πŸ’Ύ

Compute Threshold

~5.3GB VRAM

Interactive
Estimate fit
β–Ό

* Static estimation for 4-Bit Quantization.

πŸ“œ

Cite this model

Academic & Research Attribution

BibTeX 
@misc{typhoon_ai_typhoon_ocr_3b,
  author = {Typhoon Ai},
  title = {Typhoon Ocr 3b Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/typhoon-ai/typhoon-ocr-3b}},
  note = {Accessed via Free2AITools.}
}
APA Style
Typhoon Ai. (2026). Typhoon Ocr 3b [Model]. Free2AITools. https://huggingface.co/typhoon-ai/typhoon-ocr-3b

πŸ”¬Technical Deep Dive

Full Specifications [+]

Quick Commands

πŸ¦™ Ollama Run
ollama run typhoon-ocr-3b
πŸ€— HF Download
huggingface-cli download typhoon-ai/typhoon-ocr-3b
πŸ“¦ Install Lib
pip install -U transformers

βš–οΈ Free2AITools Nexus Index V2.0

Methodology How FNI works
Semantic (S) 50

Query-time baseline · scored live at search

Authority (A) 44
Popularity (P) 39
Recency (R) 100
Quality (Q) 65

πŸ’¬ Index Insight

FNI V2.0 for Typhoon Ocr 3b: Authority (A:44), Popularity (P:39), Recency (R:100), Quality (Q:65). Semantic (S) is a query-time baseline scored live at search.

Free2AITools Nexus Index

Data Sources / Provenance

HuggingFace API GitHub Metadata Arxiv Citation DB Methodology
Open data Updated: Live data
---

πŸš€ What's Next?

πŸ“Š

Models in this category

Browse models in the same category

⚑

Deployment reference

Understand deployment options

Technical Deep Dive

⚠️ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source β†’

πŸ“ Limitations & Considerations

  • β€’ Benchmark scores may vary based on evaluation methodology and hardware configuration.
  • β€’ VRAM requirements are estimates; actual usage depends on quantization and batch size.
  • β€’ FNI scores are relative rankings and may change as new models are added.
  • ⚠ License Unknown: Verify licensing terms before commercial use.

Social Proof

HuggingFace Hub
4.9KDownloads
Hub Discussions
πŸ€— Data Source: Hugging Face β†—
πŸ”„ Updated daily

Source summary: Based on Hugging Face metadata. Not a recommendation.

πŸ“Š FNI Methodology πŸ“š Knowledge Baseℹ️ Verify with original source

πŸ›‘οΈ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

πŸ†” Identity & Source

id
hf-model--typhoon-ai--typhoon-ocr-3b
slug
typhoon-ai--typhoon-ocr-3b
source
huggingface
author
Typhoon Ai
license
Apache-2.0
tags
transformers, safetensors, qwen2_5_vl, image-text-to-text, ocr, vision-language, document-understanding, multilingual, conversational, en, th, arxiv:2601.14722, base_model:qwen/qwen2.5-vl-3b-instruct, base_model:finetune:qwen/qwen2.5-vl-3b-instruct, license:apache-2.0, text-generation-inference, endpoints_compatible, region:us

βš™οΈ Technical Specs

architecture
Qwen2_5_VLForConditionalGeneration
params billions
3.75
context length
32,768
pipeline tag
image-text-to-text
vram gb
5.3
vram is estimated
true
vram formula
VRAM β‰ˆ (params * 0.75) + 2GB (KV) + 0.5GB (OS)

πŸ“Š Engagement & Metrics

downloads
4,920
stars
null
forks
null

Data indexed from public sources. Updated daily.