Cohere-embed-multilingual-v3.0
This repository contains the tokenizer for the Cohere embed-multilingual-v3.0 model, which can be used for semantic search via the Cohere API, AWS SageMaker, or private deployments.
Fact sheet
Parameters
Context length
Architecture
Shape
Weights stored as
Task
Languages
Built on
Released
Last updated
Downloads (last 30 days)
Licence and access
Licence
Access
Security
Hugging Face security scan
Weight files by format
Facthory’s checks
The repository holds no weight files.
The scan has not finished.
The card declares no licence.
The card reports no safety evaluation.
GPU calculator
How much memory this model needs to serve at a quantization, context and number of concurrent sequences, which GPUs hold it, and how fast it can generate. Estimates from the model’s published size and shape, with the assumptions below.
The hub publishes no parameter count for this model, so the calculator cannot size it.
Profile
Kind
Lineage
Family
Uses
In and out
Written on 11 Nov 2026 by Workers AI (@cf/zai-org/glm-4.7-flash) from the model card and the hub’s metadata: a reading of the publisher’s text, not checked by Facthory.
Published benchmarks
As the model card publishes them, with the source the card names. Facthory has not run them; results are self-reported unless the hub verified them.
| Benchmark | Metric | Result | Source | Counts toward |
|---|---|---|---|---|
| MTEB AmazonCounterfactualClassification (en) en · test Not counted: not on our list | accuracy | 77.85 | Model card | Not counted: not on our list |
| MTEB AmazonCounterfactualClassification (en) en · test Not counted: not on our list | ap | 41.53 | Model card | Not counted: not on our list |
| MTEB AmazonCounterfactualClassification (en) en · test Not counted: not on our list | f1 | 71.95 | Model card | Not counted: not on our list |
| MTEB AmazonPolarityClassification default · test Not counted: not on our list | accuracy | 95.6 |
EU AI Act
What the EU AI Act asks of a general-purpose AI model depends on who places it on the EU market and how. These facts bear on it:
- Licence: No licence declared
- Access: Weights download without approval
- Parameters: not published
General-purpose AI model (Article 3(63))
Not determined. No estimate of its training compute is published, and the Commission’s indicative criterion (10²³ FLOP) needs one. If it is a general-purpose AI model, the obligations below bind its provider.
Systemic risk (Article 51)
Not presumed. No estimate of its training compute is published; without one, or a designation by the Commission under Article 52, Article 55 does not apply.
Open-source exemption (Article 53(2))
Does not apply. The card declares no licence.
General-Purpose AI Code of Practice
Cohere signed it, by the European Commission’s list of signatories. The Code is voluntary; signing it shows how a provider means to meet Articles 53 and 55.
What the card and the provider document
The card publishes almost none of the technical documentation’s items.
