granite-switch-4.1-3b-preview

Checkpointibm-granite/granite-switch-4.1-3b-previewModel card indexedModel card

Support summary

granite-switch-4.1-3b-preview is a checkpoint published by IBM, built on the GraniteSwitchForCausalLM architecture. No indexed engine release, recipe, or architecture listing documents support yet. That does not mean the model is incompatible.

Configured context
131,072 tokens
License
apache-2.0
Hugging Face model card
Publisher
IBM
Task
text generation
License
apache-2.0
Library
transformers
Architecture
GraniteSwitchForCausalLM
Weight tensor elements
4.1B
Tensor types
I64, BF16
Configured context
131,072 tokens
Weight access
Public
Repository created
2026-05-01
Source 1: ibm-granite/granite-switch-4.1-3b-preview · publisher model cardSource 2: ibm-granite/granite-switch-4.1-3b-preview · Hugging Face metadataSource 3: ibm-granite/granite-switch-4.1-3b-preview · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for granite-switch-4.1-3b-preview
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedNo matching evidence curatedNo supported release indexed
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 indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1