Hugging Face· PlatformNew model

Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents

IBM and Hugging Face announce Granite 4.0 3B Vision, a compact vision-language model for enterprise document understanding, featuring table extraction, chart understanding, and semantic KVP extraction. It is built as a LoRA adapter on Granite 4.0 Micro, using the ChartNet dataset and DeepStack architecture.

From the source

Today we're excited to announce Granite 4.0 3B Vision, a compact vision-language model (VLM) designed for enterprise document understanding.

huggingface.co

Announced

31 Mar 2026 15:10 UTC

Detected

03 Aug 2026 21:12 UTC (+125d after)