nli-MiniLM2-L6-H768: Open-Weight Model

Runs On

What it takes to serve nli-MiniLM2-L6-H768 (82M 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	0.2 GB	0.2 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	0.1 GB	0.1 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	0.0 GB	0.0 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.

Model Card

By Sentence Transformers - Cross-Encoders, published under apache-2.0, revision b95119ce93d3.

Cross-Encoder for Natural Language Inference

This model was trained using SentenceTransformers Cross-Encoder class.

Training Data

The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral.

Performance

For evaluation results, see SBERT.net - Pretrained Cross-Encoder.

Usage

Pre-trained models can be used like this:

from sentence_transformers import CrossEncoder
model = CrossEncoder('cross-encoder/nli-MiniLM2-L6-H768')
scores = model.predict([('A man is eating pizza', 'A man eats something'), ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')])

#Convert scores to labels
label_mapping = ['contradiction', 'entailment', 'neutral']
labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]

Usage with Transformers AutoModel

You can use the model also directly with Transformers library (without SentenceTransformers library):

Read the full model card (236 words)

Configuration

Architecture: RobertaForSequenceClassification
Context length (tokens): 514
Layers: 6
Hidden size: 768
Feed-forward size: 3,072
Attention heads: 12
Vocabulary size: 50,265
Model type: roberta

Identity and Version

Repository: cross-encoder/nli-MiniLM2-L6-H768
Publisher: Sentence Transformers - Cross-Encoders
Task: Zero-shot classification
Modality: Text
Library: sentence-transformers
Parameters: 82M parameters
Languages: en
Revision: b95119ce93d3e065de6214e38cd4a97b0f2f2c6d
First published: 2022-03-02
Last updated: 2025-04-15

Files and Weights

24 files, 2.9 GB in total. The weights are 13 files totalling 2.9 GB in bin, onnx, safetensors.

Weights13 files · 2.9 GB

Configuration2 files · 1.1 KB

Tokenizer4 files · 2.6 MB

Documentation1 file · 2.7 KB

Other3 files · 590.4 KB

Repository1 file · 744 B

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	328.5 MB	ec9c5b6a08b6
onnx/model.onnx	Weights	328.6 MB	807d33fffefd
onnx/model_O1.onnx	Weights	328.6 MB	8a9273f027fc
onnx/model_O2.onnx	Weights	328.5 MB	1e320643f4e1
onnx/model_O3.onnx	Weights	328.5 MB	3807cf1d57f0
onnx/model_O4.onnx	Weights	164.3 MB	b031fdc4c906
onnx/model_qint8_arm64.onnx	Weights	82.8 MB	449024a8711a
onnx/model_qint8_avx512.onnx	Weights	82.8 MB	449024a8711a
onnx/model_qint8_avx512_vnni.onnx	Weights	82.8 MB	449024a8711a
onnx/model_quint8_avx2.onnx	Weights	82.8 MB	44391a5241a6
openvino/openvino_model.bin	Weights	328.5 MB	ff8b2c896de5
openvino/openvino_model_qint8_quantized.bin	Weights	82.8 MB	36b8abc21480
pytorch_model.bin	Weights	328.5 MB	768059960825
config.json	Configuration	875 B	—
special_tokens_map.json	Configuration	239 B	—
README.md	Documentation	2.7 KB	—
CESoftmaxAccuracyEvaluator_AllNLI-dev_results.csv	Other	335 B	—
openvino/openvino_model.xml	Other	211.7 KB	—
openvino/openvino_model_qint8_quantized.xml	Other	378.3 KB	—
.gitattributes	Repository	744 B	—
merges.txt	Tokenizer	456.4 KB	—
tokenizer.json	Tokenizer	1.4 MB	—
tokenizer_config.json	Tokenizer	330 B	—
vocab.json	Tokenizer	798.3 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 2.9 GB

Download from Sentence Transformers - Cross-Encoders

Released by Sentence Transformers - Cross-Encoders through its official repository on Hugging Face. Read the license.

Built From

Derived from nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large
Quantized from nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large
Trained on (disclosed) nyu-mll/multi_nli
Trained on (disclosed) stanfordnlp/snli

Memory Requirements

Precision	Weights in memory
As published	2.9 GB
16-bit	0.2 GB
8-bit	0.1 GB
4-bit	0.0 GB

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

Questions About nli-MiniLM2-L6-H768

How much GPU memory does nli-MiniLM2-L6-H768 need?

About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (82M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run nli-MiniLM2-L6-H768 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 nli-MiniLM2-L6-H768 commercially?

Yes. nli-MiniLM2-L6-H768 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 nli-MiniLM2-L6-H768's context length?

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

Similar Models

Model · Zero-shot classification

nli-distilroberta-base

Sentence Transformers - Cross-Encoders

This model was trained using SentenceTransformers Cross-Encoder class. The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral. For evaluation results, see SBERT.net - Pretrained Cross-Encoder. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library): This model can also be used for zero-shot-classification

Open weights apache-2.0 82M parameters 514 tokens sentence-transformers

View model

Model · Zero-shot classification

nli-deberta-v3-xsmall

Sentence Transformers - Cross-Encoders

This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-xsmall The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral. For futher evaluation results, see SBERT.net - Pretrained Cross-Encoder. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library): This model can also be used for zero-shot-classification

Open weights apache-2.0 71M parameters 512 tokens sentence-transformers

View model

Model · Zero-shot classification

DeBERTa-v3-xsmall-mnli-fever-anli-ling-binary

Moritz Borrett-Laurer (formerly Laurer)

This model was trained on 782 357 hypothesis-premise pairs from 4 NLI datasets: MultiNLI, Fever-NLI, LingNLI and ANLI. Note that the model was trained on binary NLI to predict either "entailment" or "not-entailment". This is specifically designed for zero-shot classification, where the difference between "neutral" and "contradiction" is irrelevant. The base model is DeBERTa-v3-xsmall from Microsoft. The v3 variant of DeBERTa substantially outperforms previous versions of the model by including a different pre-training objective, see the DeBERTa-V3 paper. For highest performance (but less speed), I recommend using…

Open weights mit 71M parameters 512 tokens transformers

View model

Model · Zero-shot classification

deberta-v3-xsmall-zeroshot-v1.1-all-33

Moritz Borrett-Laurer (formerly Laurer)

This model was fine-tuned using the same pipeline as described in the model card for MoritzLaurer/deberta-v3-large-zeroshot-v1.1-all-33 and in this paper. The foundation model is microsoft/deberta-v3-xsmall. The model only has 22 million backbone parameters and 128 million vocabulary parameters. The backbone parameters are the main parameters active during inference, providing a significant speedup over larger models. The model is 142 MB small. This model was trained to provide a small and highly efficient zeroshot option, especially for edge devices or in-browser use-cases with transformers.js. For usage instructions and other details refer to this model card…

Open weights mit 71M parameters 512 tokens transformers

View model

Model · Zero-shot classification

distilbert-base-uncased-mnli

Typeform

This is the uncased DistilBERT model fine-tuned on Multi-Genre Natural Language Inference (MNLI) dataset for the zero-shot classification task. This model can be used for text classification tasks. CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). This model of DistilBERT-uncased is pretrained on the Multi-Genre Natural Language Inference (MultiNLI) corpus. It is a crowd-sourced collection of 433k sentence pairs annotated with textual entailment…

Open weights 67M parameters 512 tokens transformers

View model

Model · Zero-shot classification

multilingual-MiniLMv2-L6-mnli-xnli

Moritz Borrett-Laurer (formerly Laurer)

multilingual - zero-shot-classification - text-classification - nli - pytorch - accuracy - multinli - xnli pipelinetag: zero-shot-classification candidatelabels: "politics, economy, entertainment, environment" This multilingual model can perform natural language inference (NLI) on 100+ languages and is therefore also suitable for multilingual zero-shot classification. The underlying multilingual-MiniLM-L6 model was created by Microsoft and was distilled from XLM-RoBERTa-large (see details in the original paper and newer information in this repo). The model was then fine-tuned on the XNLI dataset, which contains hypothesis-premise pairs from 15 languages, as well as the English MNLI dataset.…

Open weights mit 107M parameters 514 tokens transformers

View model