This model is a quantized version of the original model intfloat/e5-mistral-7b-instruct. It's quantized using the BitsAndBytes library to 4-bit using the bnb-my-repo space. - bnb4bitquanttype: nf4 - bnb4bitusedoublequant: True - bnb4bitcomputedtype: bfloat16 - bnb4bitquantstorage: uint8 Improving Text Embeddings with Large Language Models. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024 This model has 32 layers and the embedding size is 4096. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. Have a look at configsentencetransformers.json for the prompts that are pre-configured, such as websearchquery…
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.
Parameters7.6B
Context40,960
Weights15.1 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads2.6M
Runs On
What it takes to serve Qwen3-Embedding-8B (7.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 15.1 GB | 18.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 7.6 GB | 9.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 3.8 GB | 4.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
SAVRN's Notes on Qwen3-Embedding-8B
Eighteen gigabytes decides the hardware here. At 16-bit the weights take 15.1 GB and the model needs 18.2 GB to run, under a tenth of the 192 GB on the single MI300X we list as the cheapest setup at $1.85 an hour. Do not hand that card to one embedding model; at 4-bit it needs 4.5 GB, so run it as a co-tenant beside a generation model. The 40,960-token context is what 7.6 billion parameters buy: a whole filing embedded in one pass.
Apache 2.0 allows commercial use, modification and redistribution; keep the license and copyright notices and any NOTICE file, and state significant changes if you ship a fine-tuned derivative. Confirm your stack loads sentence-transformers, and note the lineage: derived from Qwen3-8B-Base, described in arXiv:2506.05176, with 0.6B and 4B siblings and matching rerankers. No host price per million tokens yet, so budget from the card rate.
Model Card
By Qwen, published under apache-2.0, revision 1d8ad4ca9b3d.
## Highlights The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. **Exceptional Versatility**: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks **No.1** in the MTEB multilingual leaderboard (as of June 5, 2025, score **70.58**), while the reranking model excels in various text retrieval scenarios. **Comprehensive Flexibility**: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and…
Configuration
- Architecture
- Qwen3ForCausalLM
- Context length (tokens)
- 40,960
- Layers
- 36
- Hidden size
- 4,096
- Feed-forward size
- 12,288
- Attention heads
- 32
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 151,665
- RoPE base
- 1,000,000
- Stored precision
- bfloat16
- Model type
- qwen3
Identity and Version
- Repository
- Qwen/Qwen3-Embedding-8B
- Publisher
- Qwen
- Task
- Feature extraction
- Modality
- Text
- Library
- sentence-transformers
- Parameters
- 7.6B parameters
- Languages
- Not stated by the source
- Revision
- 1d8ad4ca9b3dd8059ad90a75d4983776a23d44af
- First published
- 2025-06-03
- Last updated
- 2025-07-07
Files and Weights
17 files, 15.2 GB in total. The weights are 4 files totalling 15.1 GB in safetensors.
Weights4 files · 15.1 GB
Configuration6 files · 32.2 KB
Tokenizer4 files · 15.9 MB
Documentation2 files · 28.6 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00004.safetensors | Weights | 4.9 GB | 99b343597fe8 |
| model-00002-of-00004.safetensors | Weights | 4.9 GB | dff635b0f6db |
| model-00003-of-00004.safetensors | Weights | 5.0 GB | 30b1d4c53d84 |
| model-00004-of-00004.safetensors | Weights | 335.6 MB | 36cbc9c60375 |
| 1_Pooling/config.json | Configuration | 313 B | — |
| config.json | Configuration | 729 B | — |
| config_sentence_transformers.json | Configuration | 215 B | — |
| generation_config.json | Configuration | 117 B | — |
| model.safetensors.index.json | Configuration | 30.4 KB | — |
| modules.json | Configuration | 349 B | — |
| LICENSE | Documentation | 11.3 KB | — |
| README.md | Documentation | 17.3 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 83cdf8c3a34f |
| tokenizer_config.json | Tokenizer | 7.3 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 15.1 GB
Download from Qwen
Released by Qwen through ModelScope. Read the license.
Built From
- Derived from Qwen/Qwen3-8B-Base
- Described by arXiv:2506.05176
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 15.1 GB |
| 16-bit | 15.1 GB |
| 8-bit | 7.6 GB |
| 4-bit | 3.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
- Derived fromOcten-Embedding-8B
Compare Qwen3-Embedding-8B
Questions About Qwen3-Embedding-8B
How much GPU memory does Qwen3-Embedding-8B need?
About 18.2 GB at 16-bit and 4.5 GB at 4-bit: the weights (7.6B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Qwen3-Embedding-8B on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Qwen3-Embedding-8B commercially?
Yes. Qwen3-Embedding-8B is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is Qwen3-Embedding-8B's context length?
40,960 tokens, from the maximum position embeddings in its published configuration.
Similar Models
GPTQ Quantized Qwen/Qwen3-Embedding-4B with THUIR/T2Ranking and m-a-p/COIG-CQIA for calibration set. ~0.72% lost in C-MTEB. Evaluation performed with official code. pip install compressed-tensors optimum and auto-gptq / gptqmodel, then goto the official usage guide.
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. Exceptional Versatility: The…
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Vela Omni Mini maps text, images, and speech into a shared embedding space for multimodal search, routing, and use a 0–100 scale; higher is better. All applicable models use the same examples and retrieval pools. N/A denotes a modality the text-only model does not support. Bold Vela scores improve on multi-modal-embed-large. Macro-F1 gives equal weight to every intent class (77 for Banking77 and 60 for MASSIVE), complementing the query-weighted accuracy; undefined class F1 is zero. Text evaluation uses fixed class prototypes: 3,080 Banking77 and 2,972 MASSIVE English queries. Vela Omni is adapted using training examples and intent labels from these two datasets; comparison models are…
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining. Exceptional Versatility: The…