Model Follower.

Up to date

Rebuilt
2026-10-25 06:54 UTC
Release radar
117 on watch
Hub snapshot
2026-10-25
Re-checked
daily · every number sourced and dated

Models › Qwen3-Embedding family

Qwen3-VL-Embedding-2B

Hugging Face ↗ Follow changes

Qwen Apache 2.0 out 10 months ago

2.13B parameters, text in, embeddings out, 256K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #25 in Embeddings · score 96.3 method v1 Sources 3 Downloads 30d 746.9k · #134 of 619 tracked

Changed this week: 2 new quantized builds on the Hub (28 in all).2026-10-24

Can I run it?1.3GB at INT4Estimatefits a 16 GB cardmethod
Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24
Do people use it?746.9kdownloads, 30 days#134 of 619 we track · top 22%+7 likes, downloads −10% this week484 likesHugging Face2026-10-24

Worth reading

Picked by rule from 3 tracked pieces: the lab's own post, the most shared, a field report, the latest.

3 best of 3 tracked

The 1 pick above, plus these 2. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

  1. ArticleQwen3 Embedding:Advancing Text Embedding and Reranking Through Foundation Modelsqwenlm.github.io · 2025-06-05 · 3 HN pts · official
  2. ArticleFine-Tuning Qwen3 Embeddings for product category classificationblog.ivan.digital · 2026-03-03 · 2 HN pts

Where to run it

Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.

#Cheapest live rowIn /1MOut /1MContextQuantSeen
1 HF Inference — — — — Oct 25

All 1 provider →

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.

Served by 1 API provider; 28 quantized builds for local use.

  • As a service1HF Inference
  • On own hardware28quantized builds
  • Built on2314 fine-tunes · 9 adapters · 0 merges
  • In apps16Hugging Face Spaces

Top Spaces running it: baohuynhbk14/Qwen3-VL-Multimodal-Search-DEMO ♥ 17 · nanovdr/NanoVDR-Demo ♥ 3 · lablab-ai-amd-developer-hackathon/ROCKIT-Vision-Intelligence ♥ 1

Will it fit?

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

Fits a 16 GB card at INT4

About 1.3 GB at INT4, 2.6 GB at FP8, 5.1 GB at BF16: weights only, so leave room for the KV cache.

16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 1.3 GB of weights (estimate; KV cache and activations extra)INT41.3 GBFP8: about 2.6 GB of weights (estimate; KV cache and activations extra)FP82.6 GBBF16: about 5.1 GB of weights (estimate; KV cache and activations extra)BF165.1 GB
16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 1.3 GB of weights (estimate; KV cache and activations extra)INT41.3 GBFP8: about 2.6 GB of weights (estimate; KV cache and activations extra)FP82.6 GBBF16: about 5.1 GB of weights (estimate; KV cache and activations extra)BF165.1 GB

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

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 (2026-01-07), amber triangles are 3 dated articles (each links to it), grey ticks are repo commits.

JulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2026-04-16: 1 repo commit2026-01-19: 1 repo commit2026-01-09: 1 repo commit2026-01-08: 5 repo commits2026-01-07: 3 repo commitsQwen3 Embedding:Advancing Text Embedding and Reranking Through Foundation Models · 2025-06-05Qwen3 Embedding: Advancing Text Embedding and Reranking with Foundation Models · 2025-06-11Fine-Tuning Qwen3 Embeddings for product category classification · 2026-03-03Weights 2026-01-07 · 2026-01-07Weights 2026-01-07now · 1 provider
JulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2026-04-16: 1 repo commit2026-01-19: 1 repo commit2026-01-09: 1 repo commit2026-01-08: 5 repo commits2026-01-07: 3 repo commitsQwen3 Embedding:Advancing Text Embedding and Reranking Through Foundation Models · 2025-06-05Qwen3 Embedding: Advancing Text Embedding and Reranking with Foundation Models · 2025-06-11Fine-Tuning Qwen3 Embeddings for product category classification · 2026-03-03Weights 2026-01-07 · 2026-01-07Weights 2026-01-07now · 1 provider

What people built on it

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

51 derivatives on the Hub, most of them quantized

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

28 quantized (Hugging Face model tree)14 fine-tunes (Hugging Face model tree)9 adapters (Hugging Face model tree)28 quantized14 fine-tunes9 adapters
28 quantized (Hugging Face model tree)14 fine-tunes (Hugging Face model tree)9 adapters (Hugging Face model tree)28 quantized14 fine-tunes9 adapters
GGUF DevQuasar/Qwen.Qwen3-VL-Embedding-2B-GGUF for llama.cpp, Ollama, LM Studio 240.1k downloads MLX starkdmi/Qwen3-VL-Embedding-2B-mlx-5bit for Apple silicon 550 downloads AWQ LifetimeMistake/Qwen3-VL-Embedding-2B-AWQ-4bit for vLLM, SGLang 455.6k downloads

All variants →

Reference

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

Benchmarks

29 rows

Benchmarks 29 rows

measured third-party leaderboard rowauthor-reported number from the model card or eval files (29)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.
BenchmarkValueSetting / notesReported byDate
author-reported MMEB · Embed text for search70.3Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search74.3Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search74.8Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search88.5Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search75Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search71.9Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search64.9Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search53.9Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search53.3Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search61.9Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search84.4Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search65.3Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search86.4Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search69.4Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search86.4Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search79.2Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search69.4Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MMEB · Embed text for search73.2Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search63.87Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search55.84Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search69.51Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search65.86Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search52.5Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search3.87Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search26.08Qwen3-VL-Embedding-2Bmodel author2026-10-07
Show all 29 rows (4 more)
BenchmarkValueSetting / notesReported byDate
author-reported MTEB · Embed text for search78.5Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search64.8Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search67.12Qwen3-VL-Embedding-2Bmodel author2026-10-07
author-reported MTEB · Embed text for search74.29Qwen3-VL-Embedding-2Bmodel author2026-10-07

What the card says

1 cited sentence

Summary generated, cited

It supports text, images, screenshots, and videos under an Apache 2.0 license.[1][2]

  1. license
  2. “Text, images, screenshots, videos”

Generated 2026-10-07 15:01 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.

Use-case evidence

7 use cases

What it is good at 7 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

21 fields

Listed in Embeddings

Facts

Pipeline tagsentence-similarity
Librarysentence-transformers
ArchitecturesQwen3VLForConditionalGeneration
Model typeqwen3_vl
Dtypebfloat16
Params by dtypeBF16: 2,127,532,032
Size bandM
MoEno
Context length262,144 (config.json max_position_embeddings)
PapersarXiv:2601.04720
LicenseApache 2.0 (apache-2.0)
Hub snapshot2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · Qwen3VLForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen3VLForConditionalGeneration · 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 Qwen3-VL-Embedding-2B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)5.1 GB · Single GPU (<24 GB)
FP8 (1 byte/param)2.6 GB · Edge (<4 GB)
INT4 (0.5 bytes/param)1.3 GB · Edge (<4 GB)

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

All variants

40 variants

Lineage

Fine-tuned from Qwen/Qwen3-VL-2B-Instruct (same organization) Family: Qwen/Qwen3-Embedding 51 derivatives on the Hub

Base model: Qwen/Qwen3-VL-2B-Instruct

quantized: 28finetune: 14adapter: 9

Top variants (40 shown, ranked by downloads)

Relation
Quant
Size
40 rows
Variant Relation Quant Params Band License Author Likes Downloads
LifetimeMistake/Qwen3-VL-Embedding-2B-AWQ-4bit quantized AWQ 2.46B M apache-2.0 LifetimeMistake 2 455.6k
DevQuasar/Qwen.Qwen3-VL-Embedding-2B-GGUF quantized GGUF — — — DevQuasar 25 240.1k
shigureui/Qwen3-VL-Embedding-2B-FP8 quantized -FP8 2.13B M mit shigureui 2 103.5k
alexliap/Qwen3-VL-Embedding-2B-FP8-DYNAMIC quantized -FP8 2.13B M apache-2.0 alexliap 7 29.6k
mradermacher/Qwen3-VL-Embedding-2B-GGUF quantized GGUF — — apache-2.0 mradermacher 2 11.4k
LifetimeMistake/Qwen3-VL-Embedding-2B-NVFP4 quantized NVFP4 1.51B S apache-2.0 LifetimeMistake 2 7.6k
jfiekdjdk/Qwen3-VL-Embedding-2B-Q8_0-GGUF quantized Q8_0 — — apache-2.0 jfiekdjdk 6 4.5k
mradermacher/Qwen3-VL-Embedding-2B-i1-GGUF quantized GGUF — — apache-2.0 mradermacher 2 4.6k
tomaarsen/Qwen3-VL-Embedding-2B-vdr finetune — 2.13B M apache-2.0 tomaarsen 5 4.4k
dnotitia/DNA-VL-STEER-2B finetune — 2.13B M apache-2.0 dnotitia 14 3.8k
alpaim/Qwen3-VL-Embedding-2B-GGUF-vecBox quantized GGUF — — — alpaim 1 3.3k
EximiusLabs/fusion-embedding-1-2b-preview finetune — 16.4M S cc-by-nc-4.0 EximiusLabs 12 1.9k
EximiusLabs/fusion-embedding-2-2b-preview finetune — 60.6M S cc-by-nc-4.0 EximiusLabs 10 1.7k
Rizwan313/Qwen3-VL-Embedding-2B-GGUF quantized GGUF — — apache-2.0 Rizwan313 0 1.9k
TitleOS/Qwen3-VL-Embedding-2B-GGUF quantized GGUF — — apache-2.0 TitleOS 2 1.8k
batiai/Qwen3-VL-Embedding-2B-GGUF quantized GGUF — — apache-2.0 batiai 0 1.9k
whybe-choi/kovre finetune — 2.13B M apache-2.0 whybe-choi 5 888
whybe-choi/kovre-stage1 finetune — 2.13B M apache-2.0 whybe-choi 2 722
Urock-AI/Eddy-vl_embedding_1.9B_v1 finetune — 1.93B S apache-2.0 Urock-AI 6 455
S1M0N38/Qwen3-VL-Embedding-2B-Q4_K_M-GGUF quantized GGUF — — apache-2.0 S1M0N38 1 652
ifire/Qwen3-VL-Embedding-2B-GGUF quantized GGUF — — apache-2.0 ifire 0 573
starkdmi/Qwen3-VL-Embedding-2B-mlx-5bit quantized mlx 2.13B M apache-2.0 starkdmi 0 550
VesNFF/Qwen3-VL-Embedding-2B-GGUF quantized GGUF — — apache-2.0 VesNFF 0 503
AhmedxSaad/Qwen3-VL-Embedding-2B-Q4_K_M-GGUF quantized GGUF — — apache-2.0 AhmedxSaad 0 502
racineai/NATOTAN adapter — 2.13B M apache-2.0 racineai 3 286
Etherll/Qwen3-VL-Embedding-2B-Q8_0-GGUF quantized Q8_0 — — apache-2.0 Etherll 1 362
elVlad/Qwen3-VL-Embedding-2B-Q4_K_M-GGUF quantized GGUF — — apache-2.0 elVlad 0 406
johnandru/ko-vdr-preview adapter — 2.13B M apache-2.0 johnandru 6 97
turingevo/Qwen3-VL-Embedding-2B-Q4_K_M-GGUF quantized GGUF — — apache-2.0 turingevo 0 319
imbenwolf/Qwen3-VL-Embedding-2B-Q4_K_M-GGUF quantized GGUF — — apache-2.0 imbenwolf 0 311
gorse-io/Qwen3-VL-Embedding-2B-GGUF quantized GGUF — — apache-2.0 gorse-io 0 239
ganeshrao/Qwen3-VL-Embedding-2B-Q8_0-GGUF quantized Q8_0 — — apache-2.0 ganeshrao 0 201
Chrisyichuan/wiki-screenshot-embedding-lora adapter — — — apache-2.0 Chrisyichuan 4 0
staralt/Qwen3-VL-Embedding-2B-Q8_0-GGUF quantized Q8_0 — — apache-2.0 staralt 0 144
Hyphonical/Qwen3-VL-Embedding-2B-NSFW finetune — — — — Hyphonical 2 0
zhangsongbo365/Qwen3-VL-Embedding-2B-onnx quantized — — — apache-2.0 zhangsongbo365 2 0
alan314159/Qwen3-VL-Embedding-2B-Q8_0-GGUF quantized Q8_0 — — apache-2.0 alan314159 0 94
tomaarsen/ColQwen3-VL-Embedding-2B-vdr finetune — 2.13B M — tomaarsen 0 81
theblackcat102/TasteRoute-Generic-20261010 finetune — 2.13B M apache-2.0 theblackcat102 0 51
tomaarsen/ColQwen3-VL-Embedding-2B-vdr-lora finetune — — — apache-2.0 tomaarsen 1 0

Repository changelog

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

Repository changelog 11 commits

DateCommitSHA
2026-04-16 Integrate with Sentence Transformers v5.4 (#23) 9f2f7e7
2026-01-19 add model pipeline info and technical report info (#14) 2a50926
2026-01-09 Add vLLM and SGLang usage examples (#8) 929a0c3
2026-01-08 Update scripts/qwen3_vl_embedding.py (#4) 5d57766
2026-01-08 update blog link (#3) 14c71e3
2026-01-08 Update README.md bc6e454
2026-01-08 Update README.md 97bcffd
2026-01-08 Update README.md (#1) 002a899
2026-01-07 Update README.md adcbfd9
2026-01-07 Upload folder using huggingface_hub 1e6d4ea
2026-01-07 initial commit 82baf00

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Qwen3-VL-Embedding-2B, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.

ProviderModel refContextQuant$/M in$/M outtok/sTTFTToolsStatusObserved
HF Inference
hf
 Qwen/Qwen3-VL-Embedding-2B — — — — — — — live 2026-10-25

Articles and coverage

3 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.

Official1

Qwen3 Embedding:Advancing Text Embedding and Reranking Through Foundation Models
qwenlm.github.io2025-06-05officialauthorityabout the Qwen3 Embedding familyHN 3 pts · 0 comments937 words
The Qwen3-Embedding-8B model ranks No.1 in the MTEB multilingual leaderboard with a score of 70.58. The Qwen3-Reranker-4B model achieves a FollowIR score of 14.84.generated, cited

Analysis2

Qwen3 Embedding: Advancing Text Embedding and Reranking with Foundation Models
arxiv.org2025-06-11authorityabout the Qwen3 Embedding familyHN 1 pts · 0 comments433 words
The Qwen3 Embedding series introduces new text embedding and reranking models built on Qwen3 foundation models. It offers a spectrum of model sizes (0.6B, 4B, 8B) for both embedding and reranking tasks and is publicly available under the Apache 2.0 license. The series achieves strong results on the multilingual evaluation benchmark MTEB for text embedding.written, reviewed, cited
Fine-Tuning Qwen3 Embeddings for product category classification
blog.ivan.digital2026-03-03about the Qwen3 Embedding familyHN 2 pts · 0 comments

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).

Similar models

3 models

Similar models

  • snowflake-arctic-embed-l-v2.0 · 568M
    same task (sentence-similarity), permissive license
  • bge-m3
    same task (sentence-similarity), more providers, permissive license
  • LaBSE · 471M
    same task (sentence-similarity), permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:34 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:01 UTC · Last verified 2026-10-25

Follow Qwen3-VL-Embedding-2B

Watch this model

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