# snowflake-arctic-embed-l-v2.0 by Snowflake: Open Model
Source: https://savrn.com/models/snowflake-arctic-embed-l-v2-0
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Runs On

What it takes to serve snowflake-arctic-embed-l-v2.0 (568M 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 | 1.1 GB | 1.4 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |
| 8-bit | 0.6 GB | 0.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 |
| 4-bit | 0.3 GB | 0.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026.

[snowflake-arctic-embed-l-v2.0 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/snowflake-arctic-embed-l-v2-0/gpus)

## SAVRN's Notes on snowflake-arctic-embed-l-v2.0

1.4 GB at 16-bit, 0.3 GB at 4-bit for 568M parameters: another embedding model that no one rents a card for on its own — one MI300X at $1.85 an hour is the table's floor, but the honest deployment is beside your generator on hardware you already pay for. The context is 8,194 tokens, and the language list runs from Afrikaans through dozens more, so chunking behavior matters more than VRAM here.

The download is 8.3 GB spread over 10 files because the repository ships safetensors, ONNX and int8 builds together — take the one your serving stack loads, not the whole folder. Apache 2.0 covers commercial use. The evaluation table is publisher-reported MTEB only (classification and retrieval rows such as AmazonCounterfactual at 65.6 accuracy), with no third-party runs on file, so benchmark it against your own documents before trusting the marketing. Nearest neighbor on the hub: nomic-embed-text-v2-moe.

SAVRN Research

## Model Card

By Snowflake, published under apache-2.0, revision ac6544c8a46e.

### Snowflake's Arctic-embed-l-v2.0

#### News | Models | Usage | Evaluation | Contact | FAQ License | Acknowledgement

### News

- 12/11/2024: Release of [Technical Report](https://arxiv.org/abs/2412.04506)
- 12/04/2024: Release of [snowflake-arctic-embed-l-v2.0](https://savrn.com/models/snowflake-arctic-embed-l-v2-0) and [snowflake-arctic-embed-m-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0) our newest models with multilingual workloads in mind.

### Models

Snowflake arctic-embed-l-v2.0 is the newest addition to the suite of embedding models Snowflake has released optimizing for retrieval performance and inference efficiency. Arctic Embed 2.0 introduces a new standard for multilingual embedding models, combining high-quality multilingual text retrieval without sacrificing performance in English. Released under the permissive Apache 2.0 license, Arctic Embed 2.0 is ideal for applications that demand reliable, enterprise-grade multilingual search and retrieval at scale.

Key Features:

[Read the full model card (897 words)](https://savrn.com/models/snowflake-arctic-embed-l-v2-0/card)

## Configuration

Architecture

XLMRobertaModel

Context length (tokens)

8,194

Layers

24

Hidden size

1,024

Feed-forward size

4,096

Attention heads

16

Vocabulary size

250,002

Stored precision

float32

Model type

xlm-roberta

## Identity and Version

Repository

Snowflake/snowflake-arctic-embed-l-v2.0

Publisher

Snowflake

Task

Sentence similarity

Modality

Text

Library

sentence-transformers

Parameters

568M parameters

Languages

af, ar, az, be, bg, bn, ca, ceb

Revision

ac6544c8a46e00af67e330e85a9028c66b8cfd9a

First published

2024-11-08

Last updated

2025-07-28

## Files and Weights

22 files, 10.6 GB in total. The weights are 10 files totalling 8.3 GB in onnx, safetensors.

Weights10 files · 8.3 GB

Configuration5 files · 2.6 KB

Tokenizer2 files · 17.1 MB

Documentation2 files · 501.2 KB

Other2 files · 2.3 GB

Repository1 file · 1.6 KB

Every file

| File | Type | Size | SHA-256 |
| --- | --- | --- | --- |
| model.safetensors | Weights | 2.3 GB | 21bf1a120b1c |
| onnx/model.onnx | Weights | 702.3 KB | f74aa79745cc |
| onnx/model_O4.onnx | Weights | 452.3 KB | ae7e73a69d69 |
| onnx/model_bnb4.onnx | Weights | 1.2 GB | 50d4fae23d8d |
| onnx/model_fp16.onnx | Weights | 1.1 GB | 0b6846bcf4c0 |
| onnx/model_int8.onnx | Weights | 569.7 MB | 4b164a8bd09d |
| onnx/model_q4.onnx | Weights | 1.2 GB | ec3ba7101ef4 |
| onnx/model_q4f16.onnx | Weights | 700.1 MB | 6a449f29654a |
| onnx/model_quantized.onnx | Weights | 569.7 MB | 4b164a8bd09d |
| onnx/model_uint8.onnx | Weights | 569.7 MB | 8712ea862fbb |
| 1_Pooling/config.json | Configuration | 297 B | — |
| config.json | Configuration | 818 B | — |
| config_sentence_transformers.json | Configuration | 203 B | — |
| modules.json | Configuration | 349 B | — |
| special_tokens_map.json | Configuration | 964 B | — |
| README.MD | Documentation | 250.2 KB | — |
| README.md | Documentation | 251.0 KB | — |
| onnx/model.onnx_data | Other | 2.3 GB | fe7d75ff258f |
| sentencepiece.bpe.model | Other | 5.1 MB | cfc8146abe2a |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.1 MB | 39feb9863a37 |
| tokenizer_config.json | Tokenizer | 1.3 KB | — |

## License and Download

License

apache-2.0

Access

Open weights, no gate

Download size

8.3 GB

[Download from Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0)

Released by Snowflake through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0).

## Built From

- Described by arXiv:2412.04506

## Evaluations

Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.

| Benchmark | Conditions | Result | Reported by | Revision | Date |
| --- | --- | --- | --- | --- | --- |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 65.597 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric apComparison conditions not established | 29.7621 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric ap_weightedComparison conditions not established | 29.7621 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 60.2443 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1_weightedComparison conditions not established | 68.9975 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric main_scoreComparison conditions not established | 65.597 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric accuracyComparison conditions not established | 67.039 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric apComparison conditions not established | 17.9914 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric ap_weightedComparison conditions not established | 17.9914 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric f1Comparison conditions not established | 55.1806 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric f1_weightedComparison conditions not established | 73.4115 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric main_scoreComparison conditions not established | 67.039 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification (default) | Configuration defaultTask ClassificationMetric accuracyComparison conditions not established | 74.2565 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification (default) | Configuration defaultTask ClassificationMetric apComparison conditions not established | 68.7595 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification (default) | Configuration defaultTask ClassificationMetric ap_weightedComparison conditions not established | 68.7595 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification (default) | Configuration defaultTask ClassificationMetric f1Comparison conditions not established | 74.0291 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification (default) | Configuration defaultTask ClassificationMetric f1_weightedComparison conditions not established | 74.0291 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification (default) | Configuration defaultTask ClassificationMetric main_scoreComparison conditions not established | 74.2565 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 34.946 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 34.2853 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1_weightedComparison conditions not established | 34.2853 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric main_scoreComparison conditions not established | 34.946 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric map_at_1Comparison conditions not established | 33.286 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric map_at_10Comparison conditions not established | 50.046 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric map_at_100Comparison conditions not established | 50.708 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric map_at_1000Comparison conditions not established | 50.712 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric map_at_20Comparison conditions not established | 50.56 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric map_at_3Comparison conditions not established | 45.14 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric map_at_5Comparison conditions not established | 47.939 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric ndcg_at_1Comparison conditions not established | 33.286 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric ndcg_at_10Comparison conditions not established | 59.146 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric ndcg_at_100Comparison conditions not established | 61.784 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric ndcg_at_1000Comparison conditions not established | 61.845 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric ndcg_at_20Comparison conditions not established | 60.898 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric ndcg_at_3Comparison conditions not established | 49.051 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric ndcg_at_5Comparison conditions not established | 54.107 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric recall_at_1Comparison conditions not established | 33.286 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| MTEB ArguAna (default) | Configuration defaultTask RetrievalMetric recall_at_3Comparison conditions not established | 60.384 | [Snowflake](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0) Publisher reported | Evaluated revision not stated | — |
| mteb/arguana | Task ArguAnaMetric ArguAnaSetup Obtained using MTEB v1.18.0Comparison conditions not established | 59.11 | [Obtained using MTEB v1.18.0](https://github.com/embeddings-benchmark/mteb/) Reported by a third party | Evaluated revision not stated | 2026-03-05 |
| mteb/arguana | Task ArguAna_default_testMetric ArguAna_default_testSetup Obtained using MTEB v1.18.0Comparison conditions not established | 59.11 | [Obtained using MTEB v1.18.0](https://github.com/embeddings-benchmark/mteb/) Reported by a third party | Evaluated revision not stated | 2026-03-05 |

## Memory Requirements

| Precision | Weights in memory |
| --- | --- |
| As published | 8.3 GB |
| 16-bit | 1.1 GB |
| 8-bit | 0.6 GB |
| 4-bit | 0.3 GB |

Weights only, from the published parameter count; the key-value cache and runtime add to this.

## Built on This Model

- Quantized from[snowflake-arctic-embed-l-v2.0-GGUF](https://savrn.com/models/snowflake-arctic-embed-l-v2-0-gguf)
- Derived from[snowflake-arctic-embed-l-v2.0-GGUF](https://savrn.com/models/snowflake-arctic-embed-l-v2-0-gguf)

## Questions About snowflake-arctic-embed-l-v2.0

### How much GPU memory does snowflake-arctic-embed-l-v2.0 need?

About 1.4 GB at 16-bit and 0.3 GB at 4-bit: the weights (568M parameters) plus a working margin. A long context needs more.

### What is the cheapest GPU to run snowflake-arctic-embed-l-v2.0 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 snowflake-arctic-embed-l-v2.0 commercially?

Yes. snowflake-arctic-embed-l-v2.0 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 snowflake-arctic-embed-l-v2.0's context length?

8,194 tokens, from the maximum position embeddings in its published configuration.

## Similar Models

Model · Sentence similarity

### [ateneo-bge-m3-ecuador-v2](https://savrn.com/models/ateneo-bge-m3-ecuador-v2)

[Jorge Doicela](https://savrn.com/model-publishers/doiceladev)

This is a sentence-transformers model finetuned from BAAI/bge-m3. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more. First install the Sentence Transformers library: Then you can load this model and run inference. Evaluated with InformationRetrievalEvaluator Approximate statistics based on the first 100 samples: - perdevicetrainbatchsize: 32 - numtrainepochs: 5 - learningrate: 2e-05 - lrschedulertype: cosine - warmupsteps: 0.1 - optim: adamwtorch - weightdecay: 0.01 - bf16: True - perdeviceevalbatchsize: 32 - loadbestmodelatend: True…

Open weights 568M parameters 8,194 tokens sentence-transformers

[View model](https://savrn.com/models/ateneo-bge-m3-ecuador-v2)

Model · Sentence similarity

### [AX-Qwen3-Embedding-0.6B-CUDA-AXQ-NVFP4-W4A4](https://savrn.com/models/ax-qwen3-embedding-0-6b-cuda-axq-nvfp4-w4a4)

[AutomatosX](https://savrn.com/model-publishers/automatosx)

AXQuant CUDA NVFP4 W4A4 mixed precision development preview. Converted from the original upstream BF16 source, without AWQ. Native E2M1 FP4 weights and inputs use per-16 E4M3FN scales and FP32 global scales. This is a retrieval embedding checkpoint, with no MTP or generative claim. All attention projections and the first/last two MLP blocks retain original BF16. Remaining MLP matrices use NVFP4 W4A4. Saved query instruction, last-token pooling, exactly one (151643), and L2 normalization. The chat (151645) is not appended. Factory conversion uses AXQuant's NumPy reference RTN encoder, independently checked against preserved BF16 source tensors. Source and pooling assets, calibration and…

Open weights apache-2.0 596M parameters 32,768 tokens vllm

[View model](https://savrn.com/models/ax-qwen3-embedding-0-6b-cuda-axq-nvfp4-w4a4)

Model · Sentence similarity

### [nomic-embed-text-v2-moe](https://savrn.com/models/nomic-embed-text-v2-moe)

[Nomic AI](https://savrn.com/model-publishers/nomic-ai)

This model was presented in the paper Training Sparse Mixture Of Experts Text Embedding Models. nomic-embed-text-v2-moe is a SoTA multilingual MoE text embedding model that excels at multilingual retrieval: Transformer-based text embedding models have improved their performance on benchmarks like MIRACL and BEIR by increasing their parameter counts. However, this scaling approach introduces significant deployment challenges, including increased inference latency and memory usage. These challenges are particularly severe in retrieval-augmented generation (RAG) applications, where large models' increased memory requirements constrain dataset ingestion capacity, and their higher latency…

Open weights apache-2.0 475M parameters sentence-transformers

[View model](https://savrn.com/models/nomic-embed-text-v2-moe)

Model · Sentence similarity

### [LaBSE](https://savrn.com/models/labse)

[Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers)

This is a port of the LaBSE model to PyTorch. It can be used to map 109 languages to a shared vector space. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Have a look at LaBSE for the respective publication that describes LaBSE.

Open weights apache-2.0 471M parameters 512 tokens sentence-transformers

[View model](https://savrn.com/models/labse)

Model · Sentence similarity

### [semantic-lite-2](https://savrn.com/models/semantic-lite-2)

[Zulfah](https://savrn.com/model-publishers/ukung)

Semantic-Lite-2 is a lightweight multilingual sentence embedding model that produces 256-dimensional semantic vectors. It is designed for semantic search, sentence similarity, clustering, retrieval, and retrieval-augmented generation (RAG) tasks. The model is built on top of the Spark-X2.5-1.7B backbone using a frozen-backbone plus trainable-projection-head approach. The 256-dimensional output keeps vector storage compact while preserving strong retrieval quality. Vectors are L2-normalized, so cosine similarity is computed as a simple dot product. Evaluated on 500 Indonesian NLI evaluation pairs (retrieval task, chance level 0.2%): Cross-lingual evaluation (10 languages, 20 pairs per…

Open weights apache-2.0 460M parameters 1,048,576 tokens transformers

[View model](https://savrn.com/models/semantic-lite-2)

Model · Sentence similarity

### [gte-large-en-v1.5](https://savrn.com/models/gte-large-en-v1-5)

[Alibaba-NLP](https://savrn.com/model-publishers/alibaba-nlp)

We introduce gte-v1.5 series, upgraded gte embeddings that support the context length of up to 8192, while further enhancing model performance. The models are built upon the transformer++ encoder backbone (BERT + RoPE + GLU). The gte-v1.5 series achieve state-of-the-art scores on the MTEB benchmark within the same model size category and prodvide competitive on the LoCo long-context retrieval tests (refer to Evaluation). We also present the gte-Qwen1.5-7B-instruct, a SOTA instruction-tuned multi-lingual embedding model that ranked 2nd in MTEB and 1st in C-MTEB. Models for Multilingual Text Retrieval](https://arxiv.org/pdf/2407.19669) Use the code below to get started with the model. It is…

Open weights apache-2.0 434M parameters 8,192 tokens transformers

[View model](https://savrn.com/models/gte-large-en-v1-5)

## Snowflake

[All models and datasets](https://savrn.com/model-publishers/snowflake)

## Versions

- [ac6544c8a46e](https://savrn.com/models/snowflake-arctic-embed-l-v2-0/versions/ac6544c8a46e) · current 2026-10-23

## Explore More

- [All sentence similarity models](https://savrn.com/models/tasks/sentence-similarity)
- [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0)
- [Model comparisons](https://savrn.com/models/comparisons)
- [The model directory](https://savrn.com/models)
- [Open model prices by host](https://savrn.com/ai-index/pricing/open-models)

## Source

- Repository metadata, read 2026-10-19.
- [Hugging Face record](https://huggingface.co/Snowflake/snowflake-arctic-embed-l-v2.0)
- [How the hub is built](https://savrn.com/model-hub/methodology)