nomic-embed-text-v1

137M parameters, text in, embeddings out, 8K tokens of context.

Verified 2026-10-25 Rank #32 in Embeddings · score 93.5 method v1 Sources 3 Downloads 30d 1.5M · #82 of 619 tracked

Changed this week: 2 new quantized builds on the Hub (9 in all).2026-10-24

Can I run it?0.1GB at INT4Estimatefits a 16 GB cardmethod

Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24

Does it work?63.6on MTEB#18 of 64 measuredleaderboard2026-10-24

Do people use it?1.5Mdownloads, 30 days#82 of 619 we track · top 13%+2 likes, downloads −29% this week596 likesHugging Face2026-10-24

Worth reading

Picked by rule from 10 tracked pieces: the lab's own post, the most shared, a field report, the latest.

The lab's own post

Nomic Embed Text v1 | Nomic News

nomic.ai 2024-02-01 923 words

Latest · 20 months ago

Nomic Embed Text V2: An Open Source, Multilingual, Moe Embedding Model

nomic.ai 2025-02-17 1 HN pts · 2 comments about the nomic family family

10 best of 10 tracked

The 2 picks above, plus these 8. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

PaperNomic Embed: Training a Reproducible Long Context Text Embedderarxiv.org · undated
ArticleNomic Embed: Training a Reproducible Long Context Text Embedderstatic.nomic.ai · undated · official
ArticleFast Retrieval with Resizable Embeddings | Nomic Platform Documentationdocs.nomic.ai · undated · official
ArticleNomic Embed: A Open Embedding Modelblog.nomic.ai · 2024-02-01 · 4 HN pts · official
ArticleMultimodal Embeddings for Unified Latent Space by Nomicblog.nomic.ai · 2024-06-05 · 2 HN pts · official
Article[Literature Review] Nomic Embed: Training a Reproducible Long Context Text Embedderthemoonlight.io · undated
ArticleNomic-Embed-Text-V1 Overviewemergentmind.com · undated
ArticleNomic Embed: Training a Reproducible Long Context Text Embedderexa.ai · 2024-02-02

Show all 8

Where it's used

Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.

No API provider serves it, so its downloads are people running it themselves: 9 quantized builds and 100 Spaces.

As a service0no API provider listed
On own hardware9quantized builds
Built on2323 fine-tunes · 0 adapters · 0 merges
In apps100+Hugging Face Spaces

Top Spaces running it: embedl/hfviewer ♥ 181 · harshitv804/LawGPT ♥ 10 · LAWGPT/attorneygpt ♥ 6 · emanforhelp/model-pulse ♥ 5

Will it fit?

Weights only, an estimate: leave room for the KV cache. Method

Fits a 16 GB card at INT4

About 0.1 GB at INT4, 0.2 GB at FP8, 0.3 GB at BF16: weights only, so leave room for the KV cache.

Estimate params × bytes per param × 1.2 · how we estimate

How it scores

Third-party measurements only; author-reported numbers stay in Reference, marked as such.

#18 of 64 on MTEB so far

63.6. Each tick is a model on this site with a measured MTEB row; author-reported numbers stay in Reference. Mean(task) x100 over 41 tasks. 41 tasks, split=test

Source · leaderboard · 2026-10-24

The story so far

Weights, every dated article, and repo commits on one rail.

Most coverage came in the first two weeks

Teal is the weights (2024-01-31), amber triangles are 5 dated articles (each links to it), grey ticks are repo commits.

What people built on it

32 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

32 derivatives on the Hub, most of them fine-tunes

From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.

GGUF nomic-ai/nomic-embed-text-v1-GGUF for llama.cpp, Ollama, LM Studio 99.8k downloads

All variants →

Reference

Everything else, folded: the full tables, every source.

Benchmarks

6 rows

Benchmarks 6 rows

measured third-party leaderboard row (3)author-reported number from the model card or eval files (3)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.

Benchmark	Value	Setting / notes	Reported by	Date
measured MTEB · Embed text for search	50.72 nDCG@10 x100 (mean of 10 tasks)	10 tasks, split=test	leaderboard	2026-10-24
measured MTEB · Embed text for search	63.6 mean(task) x100 over 41 tasks	41 tasks, split=test	leaderboard	2026-10-24
measured MTEB Reranking · Rerank search results	45.71 MAP x100 (mean of 2 tasks)	2 tasks, split=test	leaderboard	2026-10-24
author-reported Jina Long Context	54.16	8192	model author	2026-10-07
author-reported LoCo · Embed text for search	85.53	8192	model author	2026-10-07
author-reported MTEB · Embed text for search	62.39	8192	model author	2026-10-07

What the card says

1 cited sentence

Summary generated, cited

The model utilizes a NomicBertModel architecture and supports a context length of 8192.^[1]^[2]

architectures
“8192 context length text encoder”

Generated 2026-10-07 15:02 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

Use-case evidence

2 use cases

What it is good at 2 use cases

Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.

Facts

22 fields

Listed in Embeddings

Facts

nomic-embed-text-v1 has 137M parameters. (safetensors metadata, observed 2026-10-24)
Context length is 8,192 tokens (8K). (config.json max_position_embeddings, observed 2026-10-24)
License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
Created 2024-01-31, last modified 2026-04-07. (HF API, observed 2026-10-24)

Pipeline tag	sentence-similarity
Library	sentence-transformers
Architectures	NomicBertModel
Model type	nomic_bert
Dtype	float32
Params by dtype	F32: 136,731,648
Size band	S
MoE	no
Context length	8,192 (config.json max_position_embeddings)
Languages	en
Papers	arXiv:2402.01613
License	Apache 2.0 (apache-2.0)
Hub snapshot	2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · NomicBertModel · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed

vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.

Hardware fit

3 estimates

Hardware fit ESTIMATE

Weights-only memory for nomic-embed-text-v1: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)	0.3 GB · Edge (<4 GB)
FP8 (1 byte/param)	0.2 GB · Edge (<4 GB)
INT4 (0.5 bytes/param)	0.1 GB · Edge (<4 GB)

Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.

All variants

32 variants

Lineage

Original model Family: nomic-ai/nomic 32 derivatives on the Hub

quantized: 9finetune: 23

Top variants (32 shown, ranked by downloads)

Variant	Relation	Quant	Params	Band	License	Author	Likes	Downloads
Xenova/nomic-embed-text-v1	quantized	—	—	—	—	Xenova	6	168.4k
nomic-ai/nomic-embed-text-v1-GGUF	quantized	GGUF	—	—	apache-2.0	nomic-ai	7	99.8k
deman539/nomic-embed-text-v1	finetune	—	137M	S	—	deman539	0	435
MaxNoichl/nomic-embed-philosophy-triplets_v1	finetune	—	137M	S	—	MaxNoichl	0	382
MaxNoichl/nomic-embed-philosophy-triplets_v3	finetune	—	137M	S	—	MaxNoichl	0	354
chingizof/finetune-nomic	finetune	—	137M	S	—	chingizof	0	349
Arm/nomic-embed-text-v1-int8-litert	quantized	int8	—	—	apache-2.0	Arm	0	279
MaxNoichl/nomic-embed-philosophy-triplets_v5	finetune	—	137M	S	—	MaxNoichl	0	260
MaxNoichl/nomic-embed-philosophy-triplets_v7	finetune	—	137M	S	—	MaxNoichl	0	258
MaxNoichl/nomic-embed-philosophy-triplets_v9	finetune	—	137M	S	—	MaxNoichl	0	245
ptpedroVortal/nomic_vortal_v3.2	finetune	—	137M	S	—	ptpedroVortal	1	164
kavish218/nomic_embeddings-htc-1	finetune	—	137M	S	—	kavish218	0	198
kneau007/my-classifier-4	finetune	—	137M	S	—	kneau007	2	75
kavish218/nomic_embeddings-htc-2	finetune	—	137M	S	—	kavish218	0	122
kneau007/my-classifier-7	finetune	—	137M	S	—	kneau007	0	119
aniket0898/bge-base-financial-matryoshka	finetune	—	137M	S	apache-2.0	aniket0898	0	110
ptpedroVortal/nomic_vortal_v3.4	finetune	—	137M	S	—	ptpedroVortal	0	105
kneau007/few-shot-classification-ver1	finetune	—	137M	S	—	kneau007	0	103
ptpedroVortal/nomic_vortal_v3.0	finetune	—	137M	S	—	ptpedroVortal	0	99
ptpedroVortal/nomic_vortal_v3.1	finetune	—	137M	S	—	ptpedroVortal	0	99
ptpedroVortal/nomic_vortal_v3.3	finetune	—	137M	S	—	ptpedroVortal	0	94
keisuke-miyako/nomic-embed-text-v1-onnx-fp16	quantized	-fp16	—	—	—	keisuke-miyako	0	79
kneau007/mx-1	finetune	—	137M	S	—	kneau007	0	78
keisuke-miyako/nomic-embed-text-v1-onnx-fp32	quantized	—	—	—	—	keisuke-miyako	0	67
keisuke-miyako/nomic-embed-text-v1-onnx-int8	quantized	int8	—	—	—	keisuke-miyako	0	66
kneau007/my-classifier-5	finetune	—	137M	S	—	kneau007	0	49
kneau007/my-classifier-6	finetune	—	137M	S	—	kneau007	0	32
kneau007/few-shot-classification	finetune	—	137M	S	—	kneau007	0	32
keisuke-miyako/gte-base-en-v1.5-onnx-f16	quantized	—	—	—	—	keisuke-miyako	0	31
srv-sngh/nomic-embed-text-v1-ane-fp16	finetune	-fp16	—	—	—	srv-sngh	0	13
Arm/nomic-embed-text-v1-int8-xnnpack-executorch-raspberrypi5	quantized	int8	—	—	apache-2.0	Arm	0	2
Arm/nomic-embed-text-v1-int8-xnnpack-executorch-vivo-x300	quantized	int8	—	—	apache-2.0	Arm	0	2

Repository changelog

30 commits

changed in the last 7 daysOther: 2026-10-24all changes

Repository changelog 30 commits

Date	Commit	SHA
2026-04-07	v5 Transformers (#34)	3ac47f1
2025-03-31	Update README.md (#26)	eb6b20c
2024-09-26	Add metadata link to newer version of the model (#24)	7202440
2024-08-26	Update config.json	cc62377
2024-08-26	Update config.json	282e906
2024-08-01	Update README.md (#23)	ec7a86b
2024-07-31	Update README.md	a6571e5
2024-06-05	Update README.md	0759316
2024-06-05	Update README.md	2d79bf7
2024-05-03	Update README.md	216cacb
2024-05-02	Delete configuration_hf_nomic_bert.py	2a16d3d
2024-05-02	Delete modeling_hf_nomic_bert.py	083d764
2024-05-02	Update config.json	e0830be
2024-04-02	Update config.json	02d9672
2024-03-26	Update config.json	4f15897
2024-03-26	Update config.json	a94cce3
2024-03-19	Update modeling_hf_nomic_bert.py	31d1c8f
2024-02-23	Update modeling_hf_nomic_bert.py	289f532
2024-02-14	Add `search_query: ` prefix to transformers.js sample code (#11)	c9cf92b
2024-02-09	Update modeling_hf_nomic_bert.py	69f2c81
2024-02-08	Update modeling_hf_nomic_bert.py	48b676a
2024-02-08	Update configuration_hf_nomic_bert.py	210e9ff
2024-02-08	Update modeling_hf_nomic_bert.py	2ae55f3
2024-02-05	Update README.md	ea6aaf1
2024-02-02	Update README.md	67bfab6
2024-02-02	Update README.md	5f25823
2024-02-02	Adding `safetensors` variant of this model (#5)	856ca13
2024-02-01	Add transformers.js tag and example code (#4)	98b6aaa
2024-02-01	Fixed repo name in Sentence Transformers snippet (#3)	df1749e
2024-02-01	Add ONNX weights (#2)	9eb2233

Articles and coverage

10 pieces

Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.

Official6

Nomic Embed: Training a Reproducible Long Context Text Embedder

static.nomic.aiofficialabout the nomic family6,559 words

nomic-embed-text-v1 is a 137M parameter, 8192 sequence length open-source model that outperforms OpenAI text-embedding-ada-002 and text-embedding-3-small on short and long-context benchmarks. The project releases training code, weights, and a training data loader with 235 million curated text pairs under an Apache 2 license to enable full replication. This model surpasses other open-source long-context embeddings like jina-embedding-v2-base-en across MTEB and LoCo evaluations.written, reviewed, cited

The model uses Dynamic NTK interpolation at inference to scale from a 2048 training limit to an 8192 sequence length.
Runtime is roughly 25% faster for SwiGLU compared to GeGLU when using the Flash Attention repository.
For retrieval datasets, the team mines hard negatives using gte-base if they are not already mined in the training data.

Fast Retrieval with Resizable Embeddings | Nomic Platform Documentation

docs.nomic.aiofficialabout the nomic family577 words

Nomic's open-source text encoder nomic-embed-text-v1.5 supports retrieval with resizable output dimensions ranging from a minimum of 64 to a maximum of 768. Reducing dimensions to 256 increases speed but loses accuracy, which can be recovered by collecting extra smaller dimension results and reranking against the full size embeddings.written, reviewed, cited

Nomic Embed: A Open Embedding Model

blog.nomic.ai2024-02-01officialHN 4 pts · 0 comments

Nomic Embed Text V2: An Open Source, Multilingual, Moe Embedding Model

nomic.ai2025-02-17officialabout the nomic familyHN 1 pts · 2 comments

Multimodal Embeddings for Unified Latent Space by Nomic

blog.nomic.ai2024-06-05officialabout the nomic familyHN 2 pts · 0 comments

Nomic Embed Text v1 | Nomic News

nomic.ai2024-02-01official923 words

Analysis4

Nomic Embed: Training a Reproducible Long Context Text Embedder

arxiv.orgauthorityabout the nomic family8,408 words

nomic-embed-text-v1 is a 137 million parameter text embedding model with an 8192 context length that outperforms OpenAI text-embedding-ada-002 and text-embedding-3-small on MTEB and LoCo benchmarks. The model is released under an Apache 2.0 license with full training code and curated data available for replication at https://github.com/nomic-ai/contrastors.written, reviewed, cited

The model uses a unidirectional contrastive loss from query to document instead of bidirectional approaches.
Dynamic NTK scaling maintains original position embeddings for sequences within the pretrained context length.
The training pipeline includes a stage utilizing hard negative documents specially chosen to be close to the positive document.

[Literature Review] Nomic Embed: Training a Reproducible Long Context Text Embedder

themoonlight.ioabout the nomic family

Nomic-Embed-Text-V1 Overview

emergentmind.com1,083 words

Nomic Embed: Training a Reproducible Long Context Text Embedder

exa.ai2024-02-02about the nomic family231 words

Papers

1 paper

Papers 1

arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).

Nomic Embed: Training a Reproducible Long Context Text Embedder this model

Zach Nussbaum, John X. Morris, Brandon Duderstadt +1 · 2024-02-02 · PDF · HF paper page (19 upvotes)

Similar models

3 models

Similar models

distiluse-base-multilingual-cased-v2 · 135M
same size band (S), same task (sentence-similarity), more providers, permissive license
distiluse-base-multilingual-cased-v1 · 135M
same size band (S), same task (sentence-similarity), more providers, permissive license
clip-ViT-B-32-multilingual-v1 · 135M
same size band (S), same task (sentence-similarity), more providers, permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:35 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:02 UTC · Last verified 2026-10-25

Follow nomic-embed-text-v1

Watch this model

/feeds/models/nomic-ai--nomic-embed-text-v1.xml(RSS 2.0) · every change to nomic-embed-text-v1
/feeds/families/nomic-ai--nomic.xml(RSS 2.0) · every change across the nomic family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.