# FastEmbed

- **Canonical URI:** https://www.vioscale.ai/software/fastembed
- **Category:** Embeddings Apis
- **Homepage:** https://qdrant.github.io/fastembed/
- **Also known as:** fastembed
- **Profile claimed by vendor:** no
- **Last updated:** 2026-08-26T19:32:29.063Z

## Vioscale score

**46.6 / 100**, confidence 31% (low). Computed 2026-09-01.

Composite of weighted, independently-sourced signals (no user reviews, no vendor payment).

| Signal | Score | Weight | Contribution | Evidence present |
|---|--:|--:|--:|:--:|
| capabilities | 91.6 | 0.07844444444444446 | 7.2 | ✓ |
| repo_stars | 66 | 0.026 | 1.7 | ✓ |
| integrations | 8.7 | 0.07033333333333334 | 0.6 | ✓ |
| dependent_projects | 11.6 | 0.063 | 0.7 | ✓ |
| dev_activity | 36.1 | 0.094 | 3.4 | ✓ |
| release_cadence | 81.7 | 0.052 | 4.2 | ✓ |
| security_posture | 0 | 0.073 | 0 | - |
| package_downloads | 0 | 0.136 | 0 | - |
| security_score | 0 | 0.042 | 0 | - |
| community_qa_activity | 0 | 0.063 | 0 | - |

## About

A Python library that creates vector embeddings from text and images using efficient, quantized model weights optimized for speed and local inference. Supports multiple embedding architectures including multilingual models and outperforms OpenAI's Ada-002 in accuracy.

_Independently observed._

## Platform & deployment
- **Deployment:** On-premise, Self-hosted

## Integrations (1)

_Independently observed._

- Qdrant

## Capabilities

_The capabilities that matter for Embeddings Apis. "-" = undocumented, not absent._

| Capability | Supported |
|---|:--:|
| **Capabilities** | |
| Architecture model | Open weights local |
| Matryoshka representation learning for dimension truncation | - |
| Multilingual support across 100 plus languages | ✓ |
| Binary and scalar quantization for memory reduction | ✓ |
| Cross encoder reranker API offered | ✓ |
| Late interaction architecture colbert v2 | ✓ |
| Massive context window greater than 8k tokens | ✓ |
| Multi modal image and text joint embeddings | ✓ |
| Task specific prefixes query vs document instructions | ✓ |
| Zero data retention training opt out enterprise | - |
| SOC2 type ii | - |
| Mit or apache permissive oss license | ✓ |
| Pricing model | Free open weights |

## Release history

| Version | Date | Type |
|---|---|---|
| [v0.8.0](https://github.com/qdrant/fastembed/releases/tag/v0.8.0) | 2026-03-23 | stable |
| [v0.7.4](https://github.com/qdrant/fastembed/releases/tag/v0.7.4) | 2025-12-05 | stable |
| [v0.7.2](https://github.com/qdrant/fastembed/releases/tag/v0.7.2) | 2025-08-25 | stable |
| [v0.7.1](https://github.com/qdrant/fastembed/releases/tag/v0.7.1) | 2025-06-16 | stable |
| [v0.7.0](https://github.com/qdrant/fastembed/releases/tag/v0.7.0) | 2025-05-13 | stable |
| [v0.6.1](https://github.com/qdrant/fastembed/releases/tag/v0.6.1) | 2025-04-10 | stable |
| [v0.6.0](https://github.com/qdrant/fastembed/releases/tag/v0.6.0) | 2025-02-26 | stable |
| [v0.5.1](https://github.com/qdrant/fastembed/releases/tag/v0.5.1) | 2025-01-20 | stable |
| [v0.5.0](https://github.com/qdrant/fastembed/releases/tag/v0.5.0) | 2024-12-24 | stable |
| [v0.4.2](https://github.com/qdrant/fastembed/releases/tag/v0.4.2) | 2024-11-13 | stable |
| [v0.4.1](https://github.com/qdrant/fastembed/releases/tag/v0.4.1) | 2024-10-21 | stable |
| [v0.4.0](https://github.com/qdrant/fastembed/releases/tag/v0.4.0) | 2024-10-21 | stable |
| [v0.3.5](https://github.com/qdrant/fastembed/releases/tag/v0.3.5) | 2024-08-23 | stable |
| [v0.3.4](https://github.com/qdrant/fastembed/releases/tag/v0.3.4) | 2024-07-17 | stable |
| [v0.3.1](https://github.com/qdrant/fastembed/releases/tag/v0.3.1) | 2024-06-17 | stable |

_… and 5 earlier release(s)._

## Security & compliance


Known vulnerabilities: 0 (0 in the last 12 months) ([source](https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=fastembed&per_page=100)). A count reflects scale and disclosure, not quality.

## Facts

Every value below carries its source and our confidence. Facts are re-crawled on a freshness schedule.

### integrations

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| integrations.count | 1 | [link](https://qdrant.github.io/fastembed/) | 2026-08-21 | 60% (medium) |

### activity

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| activity.commits_last_30d | 13 | [link](https://github.com/qdrant/fastembed/pulse) | 2026-08-26 | 65% (medium) |

### adoption

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| adoption.github_stars | 3,166 | [link](https://github.com/qdrant/fastembed) | 2026-08-26 | 90% (high) |
| adoption.dependent_repos | 4 | [link](https://packages.ecosyste.ms/api/v1/packages/lookup?repository_url=https%3A%2F%2Fgithub.com%2Fqdrant%2Ffastembed) | 2026-08-26 | 85% (high) |

### language

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| language.primary | Python | [link](https://github.com/qdrant/fastembed) | 2026-08-26 | 90% (high) |

### license

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| license.spdx | Apache-2.0 | [link](https://github.com/qdrant/fastembed) | 2026-08-26 | 95% (high) |

### release

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| release.cadence_days | 33 | [link](https://github.com/qdrant/fastembed/releases) | 2026-08-26 | 70% (medium) |

### security

| Attribute | Value | Source | Retrieved | Confidence |
|---|---|---|---|---|
| security.vulnerabilities | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=fastembed&per_page=100","last_12m":0,"max_severity":null}` | [link](https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=fastembed&per_page=100) | 2026-08-26 | 90% (high) |

---
*Source: Vioscale (https://www.vioscale.ai/software/fastembed). Independent, evidence-based software intelligence. Cite the canonical URI.*