Skip to content
AI Atlas
ModelActive

granite-speech-4.1-2b-plus

IBMhuggingface.co/ibm-granite/granite-speech-4.1-2b

Open in Graph
data quality53

Updated 10 h ago · first seen 11 Sept 2026

model_01M294YP7FX1SBTRV2SM4RCPT5

Overview

Identity

Identity block not returned by the API for this entity.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Hugging Face repo

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Capabilities

Modalities

Modalities unavailable.

Capabilities

  • Tool calling

    Unavailable

  • Structured output

    Unavailable

  • Reasoning

    Unavailable

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

No capability flags have been observed from a source yet — we do not infer them.

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Hardware fit37

Estimated

37 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—1.7 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—1.7 GB est.Yes
Apple M2 Ultra4bit—1.7 GB est.Yes
Apple M1 Ultra4bit—1.7 GB est.Yes
Apple M3 Max4bit—1.7 GB est.Yes
Apple M4 Max4bit—1.7 GB est.Yes
Mac Studio (Apple M5 Max)4bit—1.7 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—1.7 GB est.Yes
Apple M2 Max4bit—1.7 GB est.Yes
Apple M1 Max4bit—1.7 GB est.Yes
Apple M4 Pro4bit—1.7 GB est.Yes
Mac mini (Apple M5 Pro)4bit—1.7 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—1.7 GB est.Yes
Apple M3 Pro4bit—1.7 GB est.Yes
Apple M1 Pro4bit—1.7 GB est.Yes
Apple M2 Pro4bit—1.7 GB est.Yes
Apple M44bit—1.7 GB est.Yes
iMac (Apple M4)4bit—1.7 GB est.Yes
Mac mini (Apple M6)4bit—1.7 GB est.Yes
MacBook Air (Apple M5)4bit—1.7 GB est.Yes
MacBook Pro (Apple M5)4bit—1.7 GB est.Yes
Apple M24bit—1.7 GB est.Yes
Apple M34bit—1.7 GB est.Yes
Apple M14bit—1.7 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB1.7 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB1.7 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB1.7 GB est.Yes
NVIDIA A100 80GB4bit80 GB1.7 GB est.Yes
NVIDIA H100 SXM4bit80 GB1.7 GB est.Yes
NVIDIA H100 NVL4bit94 GB1.7 GB est.Yes
NVIDIA DGX Spark4bit128 GB1.7 GB est.Yes
NVIDIA H2004bit141 GB1.7 GB est.Yes
NVIDIA H200 NVL4bit141 GB1.7 GB est.Yes
NVIDIA B2004bit180 GB1.7 GB est.Yes
AMD Instinct MI300X4bit192 GB1.7 GB est.Yes
AMD Instinct MI325X4bit256 GB1.7 GB est.Yes
NVIDIA DGX B2004bit1,440 GB1.7 GB est.Yes
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
ANCESTORS 1granite-4.0-1b-baseIBMgranite-4.0-1b-base — IBMgranite-speech-4.1-2b-plus2.11B params · this modelgranite-speech-4.1-2b-plus — 2.11B params · this model

Papers6

Timeline1

Full timeline →

Change history20

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 12 Sept 2026 24 claims in force

Release date
16 Apr 2026
Openness
open-weights
License
Apache-2.0
Architecture
GraniteSpeechPlusForConditionalGeneration
Parameters
2.11B
Languages
multilingual, en, fr, de, es, pt
Base model
ibm-granite/granite-4.0-1b-base
File size
4.2 GB
Hugging Face repo
ibm-granite/granite-speech-4.1-2b-plus
Pipeline tag
automatic-speech-recognition
Downloads
127,388
Likes
90
Commercial use allowed
Yes
Derivatives allowed
Yes
Gated
No
Last modified
2026-06-16T18:20:43+00:00
Library name
transformers
Downloads all time
399,289
Model type
granite_speech_plus
Redistribution allowed
Yes
Tags
transformers, safetensors, granite_speech_plus, automatic-speech-recognition, multilingual, en, fr, de, es, pt
Weights available
Yes
Weights dtype
BF16
20 claims · 20 properties

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
16 Apr 2026 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Licenselicense1

Claim history for License
ValueValid from → toStatusSourceConfidenceExtractor
apache-2.0 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
GraniteSpeechPlusForConditionalGeneration → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
2.11B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Languageslanguages1

Claim history for Languages
ValueValid from → toStatusSourceConfidenceExtractor
multilingual, en, fr, de, es, pt → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Base modelbase_model1

Claim history for Base model
ValueValid from → toStatusSourceConfidenceExtractor
ibm-granite/granite-4.0-1b-base → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

File sizefile_size_gb1

Claim history for File size
ValueValid from → toStatusSourceConfidenceExtractor
4.2 GB → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
ibm-granite/granite-speech-4.1-2b-plus → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
ValueValid from → toStatusSourceConfidenceExtractor
automatic-speech-recognition → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/ibm-granite/granite-speech-4.1-2b-plus → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
127,388 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes1

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
90 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Gatedgated1

Claim history for Gated
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2026-06-16T18:20:43+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Library namelibrary_name1

Claim history for Library name
ValueValid from → toStatusSourceConfidenceExtractor
transformers → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
399,289 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
granite_speech_plus → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
transformers, safetensors, granite_speech_plus, automatic-speech-recognition, multilingual, en, fr, de, es, pt → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
ValueValid from → toStatusSourceConfidenceExtractor
BF16 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

20

Source tiers

T220

Freshest observation

10 h ago

Conflicts

None

Source documents 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/ibm-granite/granite-speech-4.1-2b-plus/raw/main/README.md model_cardT2· Quality secondary9 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/ibm-granite/granite-speech-4.1-2b-plus model_pageT2· Quality secondary10 h ago3
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=ibm-granite&p=0&sort=downloads listingT2· Quality secondary10 h ago3

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (53/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →