granite-vision-3.3-2b

Checkpointibm-granite/granite-vision-3.3-2bModel card indexedModel card

Support summary

granite-vision-3.3-2b is a checkpoint published by IBM, built on the LlavaNextForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. TensorRT-LLM lists its architecture, but not this exact checkpoint.

vLLM documents support in 14 of 20 indexed releases, from 0.20.0 to 0.28.0.

Configured context
131,072 tokens
License
apache-2.0
Hugging Face model card
Publisher
IBM
Task
image to text
License
apache-2.0
Architecture
LlavaNextForConditionalGeneration
Weight tensor elements
3B
Tensor types
BF16
Configured context
131,072 tokens
Weight access
Public
Repository created
2025-06-03
Source 1: ibm-granite/granite-vision-3.3-2b · publisher model cardSource 2: ibm-granite/granite-vision-3.3-2b · Hugging Face metadataSource 3: ibm-granite/granite-vision-3.3-2b · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for granite-vision-3.3-2b
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedCheckpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed 0.28.0This release
Features, dependencies and evidence for vLLM 0.28.0
SGLang0.5.19Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedArchitecture listed; exact checkpoint unknownNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1