Identity
- Status
- active
- Developer ID
ibm-granite/granite-embedding-107m-multilingual- Released
- Dec 18, 2024
- Version
- granite-embedding-107m-multilingual
- License
- apache-2.0
IBMGranite Embedding 107m Multilingual
granite-embedding-107m-multilingual is an open-weight text-embedding model published by IBM.
- Token context
- 1K tokens
- Inputs
- Text
- Outputs
- Embedding
- Released
- Dec 18, 2024
Providers & Pricing
1 current hosted offerings
No Directly Sourced Provider Price Yet
API pricing is provider-specific and stays unknown until a serving provider publishes an exact offering for this model version.
At a Glance
Model Facts
Capacity
- Token context
- 1K tokens
- Maximum output
- Unknown
- Total parameters
- 107M
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Embedding
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- No
- Tool calling
- No
- Capabilities
- embeddings
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesibm-granite/granite-embedding-107m-multilingual, ibm-granite/granite-embedding-107m-multilingual
Explicit Unknowns
- Maximum output
- Knowledge cutoff
- Provider pricing
Primary Evidence
Sources and Observation Date
ibm-granite/granite-embedding-107m-multilingual developer model repositoryIBM · observed Aug 28, 2026ibm-granite/granite-embedding-107m-multilingual Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026ibm-granite/granite-embedding-107m-multilingual config.json at d6cffd338414IBM · observed Aug 28, 2026ibm-granite/granite-embedding-107m-multilingual README.md at d6cffd338414IBM · observed Aug 28, 2026ibm-granite/granite-embedding-107m-multilingual immutable Hub API metadataIBM · observed Aug 28, 2026ibm-granite/granite-embedding-107m-multilingual tokenizer_config.json at d6cffd338414IBM · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
Questions
Granite Embedding 107m Multilingual FAQs
What is Granite Embedding 107m Multilingual?+
granite-embedding-107m-multilingual is an open-weight text-embedding model published by IBM. It is developed by IBM and its current sourced lifecycle status is active.
What inputs and outputs does Granite Embedding 107m Multilingual support?+
Granite Embedding 107m Multilingual's current record lists Text as input and Embedding as output.
How much context does Granite Embedding 107m Multilingual support?+
The current record lists a 1K-token context window and does not report a maximum output length.
Is Granite Embedding 107m Multilingual available through an API?+
Granite Embedding 107m Multilingual is marked as API-available. The directly sourced provider records currently include Hugging Face.
How large is Granite Embedding 107m Multilingual?+
The current record lists 107M total parameters and an unknown active parameter count. Its architecture is XLMRobertaModel.
What capabilities and tasks does Granite Embedding 107m Multilingual support?+
Granite Embedding 107m Multilingual's recorded capabilities are embeddings. Its supported tasks are embedding.
How much does Granite Embedding 107m Multilingual cost through an API?+
No directly sourced token price is currently attached to Granite Embedding 107m Multilingual. Missing prices remain unknown rather than being inferred from another model or provider.
Can Granite Embedding 107m Multilingual be self-hosted?+
Granite Embedding 107m Multilingual is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Granite Embedding 107m Multilingual have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are ibm-granite/granite-embedding-107m-multilingual.
Which models can Granite Embedding 107m Multilingual be compared with?+
The current compatible peer set includes Granite Embedding 278m Multilingual, Granite Embedding 30m English, Granite Embedding 311m Multilingual r2, Granite Embedding English r2, and Qwen3 Embedding 8B. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →