Ministral 14B
Trinity Nano Preview
4B
- Context
- 33Ktokens
- Released
- 1y ago
- Size
- 8Bparameters
Qwen3 Embedding 8B is a text embedding model from Alibaba, built on the Qwen3 foundation model as part of the Qwen3 Embedding series. Alibaba reports that at launch it placed first on the MTEB multilingual leaderboard, with a score of 70.58 as of June 5, 2025. It is intended for text embedding, retrieval, and reranking work, including multilingual and code retrieval, and supports user-defined task instructions.
How it compares
Size class
Small8BAn open-weight model of 5 to 25 billion parameters, the size that runs on a single consumer GPU.
Open models of a similar size from other labs
Vs. your stack
Add the models you use to see how this one compares.
Sign inAdditional source evidence
- Source model
- alibaba/qwen3-embedding-8b
- Source family
- qwen
- Source type
- embedding
- Last updated
- 2025-06-05
- Model context
- 33K
- Model output limit
- —
- Open weights
- Yes
- File attachments
- No
- Reasoning
- No
- Tool calling
- No
- Temperature control
- No
Downloadable weights
Complete source record (JSON)
{
"id": "alibaba/qwen3-embedding-8b",
"name": "Qwen3 Embedding 8B",
"description": "Multilingual text embedding model for retrieval, code search, classification, and clustering",
"family": "qwen",
"type": "embedding",
"last_updated": "2025-06-05",
"attachment": false,
"reasoning": false,
"tool_call": false,
"temperature": false,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 0
},
"release_date": "2025-06-05",
"open_weights": true,
"license": "Apache-2.0",
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/Qwen/Qwen3-Embedding-8B"
}
]
}Frequently asked questions
Running locally
Qwen3 Embedding 8B needs an estimated 6.1 GB at Q4, 10.3 GB at Q8, and 18.9 GB at FP16, derived from the 8B parameter count. These estimates cover weights plus about 15% and 0.5 GB for a short context.
Yes on all four. A 24 GB GPU fits at FP16 (estimated 18.9 GB), 16 GB and 12 GB GPUs fit at Q8 (estimated 10.3 GB), and an 8 GB GPU fits at Q4 (estimated 6.1 GB).
Yes. Q4 is an estimated 6.1 GB, and assuming macOS lets the GPU use about 75% of unified memory, the smallest common Mac memory size that fits Q4 is 16 GB.
Privacy and data
Yes, Qwen3 Embedding 8B has open weights, so you can self-host it for full control of your data.
Capabilities and specs
The context window of Qwen3 Embedding 8B is 33K tokens (32,768).
No, Qwen3 Embedding 8B only accepts text input. Images, audio and video are not among its supported modalities.
No, Qwen3 Embedding 8B does not support tool calling (function calling).
No, Qwen3 Embedding 8B does not support a reasoning mode.
Quality and benchmarks
Matched on model kind and release date (no comparable price), the closest alternatives are Sarvam-M by Sarvam AI, Gemma 3n E2B IT by Google DeepMind and Gemma 3n E4B IT by Google DeepMind.
Sarvam-MQwen3 Embedding 8B vs Sarvam-MGemma 3n E2B ITQwen3 Embedding 8B vs Gemma 3n E2B ITGemma 3n E4B ITQwen3 Embedding 8B vs Gemma 3n E4B IT
Versions and lineage
Both share a 33K token (32,768) context window and a June 5, 2025 release date. The listed difference is price, with Qwen3 Embedding 4B at $0.02 input and $0.00 output per 1M tokens.
Licensing and access
Qwen3 Embedding 8B is open weights, released under the Apache-2.0 license.
Yes, the Apache 2.0 license is a permissive license that allows commercial use.
Basics
Qwen made Qwen3 Embedding 8B, and it was released on June 5, 2025.
Yes, Qwen3 Embedding 8B has open weights.
Generated from Vertical Tabs data, updated November 10, 2026.
Discussion
No comments yet
Be the first to share your thoughts.