granite-speech-3.3-8b

Checkpointibm-granite/granite-speech-3.3-8bModel card indexedModel card

Support summary

granite-speech-3.3-8b is a checkpoint published by IBM, built on the GraniteSpeechForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support.

vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.

Configured context
131,072 tokens
License
apache-2.0
Hugging Face model card
Publisher
IBM
Task
automatic speech recognition
License
apache-2.0
Library
transformers
Architecture
GraniteSpeechForConditionalGeneration
Weight tensor elements
8.6B
Tensor types
BF16
Configured context
131,072 tokens
Languages
multilingual, en, fr, de, es, pt
Base models
ibm-granite/granite-3.3-8b-instruct
Weight access
Public
Repository created
2025-04-14
Source 1: ibm-granite/granite-speech-3.3-8b · publisher model cardSource 2: ibm-granite/granite-speech-3.3-8b · Hugging Face metadataSource 3: ibm-granite/granite-speech-3.3-8b · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for granite-speech-3.3-8b
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 indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1