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 › Qwen2.5 family

Qwen2.5-VL-7B-Instruct

Hugging Face ↗ Follow changes

Qwen Apache 2.0 out 21 months ago

8.29B parameters, images and text in, text out, 125K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #54 in LLMs · score 107.1 method v1 Sources 3 Downloads 30d 5.1M · #31 of 619 tracked

Can I run it?5.0GB at INT4Estimatefits a 16 GB cardmethod
Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24
Do people use it?5.1Mdownloads, 30 days#31 of 619 we track · top 5%+7 likes, downloads −2% this week1,753 likesHugging Face2026-10-24

Worth reading

Picked by rule from 30 tracked pieces: the lab's own post, the most shared, a field report, the latest.

Latest · 19 months ago

Qwen2.5-VL-32B: Smarter and Lighter

Alibaba open-sourced Qwen2.5-VL-32B-Instruct under the Apache 2.0 license, optimizing the model with reinforcement learning to improve human alignment and mathematical reasoning.

  • The model achieves significant advantages in MMMU, MMMU-Pro, and MathVista benchmarks focusing on complex, multi-step reasoning.
  • Qwen2.5-VL-32B-Instruct outperforms its predecessor Qwen2-VL-72B-Instruct by a substantial margin on the MM-MT-Bench benchmark.
qwenlm.github.io 2025-03-24 544 HN pts · 293 comments 606 words about the Qwen2.5 family family

25 best of 30 tracked

The 3 picks above, plus these 22. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.

  1. Codekev: Jev-like model built on Qwen2.5-0.5Bgithub.com · 2026-09-19
  2. ArticleQwen2.5-1M: Deploy your own Qwen with context length up to 1M tokensqwenlm.github.io · 2025-01-26 · official
  3. ArticleQwen2.5: A Party of Foundation Modelsqwenlm.github.io · 2024-09-18 · 168 HN pts · official
  4. ArticleQwen2.5-Max: Exploring the intelligence of large-scale MoE modelqwenlm.github.io · 2025-01-28 · official
  5. ArticleQwen2.5-Coder-32B is an LLM that can code well that runs on my Macsimonwillison.net · 2024-11-13
  6. ArticleQwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1Msimonwillison.net · 2025-01-26 · 98 HN pts
  7. ArticleQwen2.5-Coder Beats GPT-4o and Claude 3.5 Sonnet in Codingqwenlm.github.io · 2024-11-11 · official
  8. ArticleQwen2.5-VLqwenlm.github.io · 2025-01-27 · 8 HN pts · official
  9. ArticleCivic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt dataitsmeduncan.com · 2026-04-25 · 9 HN pts
  10. CodeQwen2.5-Coder-32B with coding abilities matching those of GPT-4ogithub.com · 2024-11-09
  11. ArticleQwen2.5 Omni: See, Hear, Talk, Write, Do It Allqwenlm.github.io · 2025-03-26 · official
  12. ArticleAlibaba Qwen2.5-Omni-7B: Open Source End-to-End Multimodal AI Modelalizila.com · 2025-03-27
  13. ArticleQwen2.5-VL-32B: Smarter and Lightersimonwillison.net · 2025-03-25 · 3 HN pts
  14. ArticleQwen2.5-Max: The Next Leap in AI Innovationmedium.com · 2025-01-29
  15. ArticleQwen2.5-Omni Technical Reporthuggingface.co · 2025-03-30
  16. PaperQwen2.5-Coder Technical Reportarxiv.org · 2024-11-11
  17. DiscussionQwen2.5-coder on the events occurring during the Tiananmen Square protestsnews.ycombinator.com · 2024-11-20
  18. PaperQwen2.5 Technical Reportarxiv.org · 2025-01-03
  19. CodeQwen2.5-VL: State-of-the-art multimodal LLMgithub.com · 2025-01-30 · 3 HN pts
  20. DiscussionNew Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarkstwitter.com · 2025-01-28
  21. ArticleQwen2.5-VL: Architecture, Data, Benchmarks and Inferencedebuggercafe.com · undated
  22. ArticleQwen2.5-VL-7B-Instruct by Qwen - Overview, Benchmarks & Hardware | Q4KM.aiq4km.ai · undated

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 Featherless — — — — 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; heavily run locally (159 quantized builds); a big base for builders (1,622 fine-tunes, adapters and merges).

  • As a service1Featherless
  • On own hardware159quantized builds
  • Built on1,6221,256 fine-tunes · 361 adapters · 5 merges
  • In apps100+Hugging Face Spaces

Top Spaces running it: KingNish/OpenGPT-4o ♥ 4,302 · prithivMLmods/Qwen-Image-Edit-2511-LoRAs-Fast ♥ 2,780 · linoyts/Qwen-Image-Edit-Angles ♥ 2,274 · prithivMLmods/FireRed-Image-Edit-1.0-Fast ♥ 1,646

Will it fit?

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

Fits a 16 GB card at INT4

About 5.0 GB at INT4, 10 GB at FP8, 20 GB at BF16: weights only, so leave room for the KV cache.

16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 5.0 GB of weights (estimate; KV cache and activations extra)INT45.0 GBFP8: about 10 GB of weights (estimate; KV cache and activations extra)FP810 GBBF16: about 20 GB of weights (estimate; KV cache and activations extra)BF1620 GB
16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 5.0 GB of weights (estimate; KV cache and activations extra)INT45.0 GBFP8: about 10 GB of weights (estimate; KV cache and activations extra)FP810 GBBF16: about 20 GB of weights (estimate; KV cache and activations extra)BF1620 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 (2025-01-26), amber triangles are 9 dated articles (each links to it), grey ticks are repo commits.

OctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2025-04-06: 1 repo commit2025-03-23: 1 repo commit2025-03-21: 1 repo commit2025-03-06: 1 repo commit2025-02-15: 1 repo commit2025-02-06: 1 repo commit2025-01-27: 4 repo commits2025-01-26: 2 repo commitsQwen2.5-VL-32B: Smarter and Lighter · 2025-03-24Qwen2.5: A Party of Foundation Models · 2024-09-18Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs · 2026-02-08Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M · 2025-01-26Qwen2.5-VL · 2025-01-27Civic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt data · 2026-04-25Qwen2.5-VL-32B: Smarter and Lighter · 2025-03-25Qwen2.5 Technical Report · 2025-01-03Qwen2.5-VL: State-of-the-art multimodal LLM · 2025-01-30Weights 2025-01-26 · 2025-01-26Weights 2025-01-26now · 1 provider
OctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2025-04-06: 1 repo commit2025-03-23: 1 repo commit2025-03-21: 1 repo commit2025-03-06: 1 repo commit2025-02-15: 1 repo commit2025-02-06: 1 repo commit2025-01-27: 4 repo commits2025-01-26: 2 repo commitsQwen2.5-VL-32B: Smarter and Lighter · 2025-03-24Qwen2.5: A Party of Foundation Models · 2024-09-18Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs · 2026-02-08Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M · 2025-01-26Qwen2.5-VL · 2025-01-27Civic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt data · 2026-04-25Qwen2.5-VL-32B: Smarter and Lighter · 2025-03-25Qwen2.5 Technical Report · 2025-01-03Qwen2.5-VL: State-of-the-art multimodal LLM · 2025-01-30Weights 2025-01-26 · 2025-01-26Weights 2025-01-26now · 1 provider

What people built on it

1,781 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.

1,781 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.

159 quantized (Hugging Face model tree)1,256 fine-tunes (Hugging Face model tree)5 merges (Hugging Face model tree)361 adapters (Hugging Face model tree)159 quantized1,256 fine-tunes5 merges361 adapters
159 quantized (Hugging Face model tree)1,256 fine-tunes (Hugging Face model tree)5 merges (Hugging Face model tree)361 adapters (Hugging Face model tree)159 quantized1,256 fine-tunes5 merges361 adapters
GGUF unsloth/Qwen2.5-VL-7B-Instruct-GGUF for llama.cpp, Ollama, LM Studio 2M downloads MLX mlx-community/olmOCR-2-7B-1025-mlx-8bit for Apple silicon 111.2k downloads AWQ Qwen/Qwen2.5-VL-7B-Instruct-AWQ for vLLM, SGLang 15.2M downloads

All variants →

Reference

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

Benchmarks

19 rows

Benchmarks 19 rows

measured third-party leaderboard rowauthor-reported number from the model card or eval files (19)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 AITZ_EM81.9 percent—model author2026-10-07
author-reported Android Control High_EM60.1 percent—model author2026-10-07
author-reported Android Control Low_EM93.7 percent—model author2026-10-07
author-reported AndroidWorld_SR25.5 percent—model author2026-10-07
author-reported CC-OCR · Extract text from documents77.8 percent—model author2026-10-07
author-reported CharadesSTA/mIoU43.6 percent—model author2026-10-07
author-reported LVBench · Understand images and video45.3 percent—model author2026-10-07
author-reported LongVideoBench54.7 percent—model author2026-10-07
author-reported MLVU · Understand images and video70.2 percent—model author2026-10-07
author-reported MMBench · Understand images and video1.79 percent—model author2026-10-07
author-reported MMStar · Understand images and video63.9 percent—model author2026-10-07
author-reported MMStar · Understand images and video63.9 percent—model author2026-10-07
author-reported MVBench69.6 percent—model author2026-10-07
author-reported MathVision · Understand images and video25.07 percent—model author2026-10-07
author-reported MobileMiniWob++_SR91.4 percent—model author2026-10-07
author-reported OCRBench · Extract text from documents864—model author2026-10-07
author-reported ScreenSpot84.7 percent—model author2026-10-07
author-reported ScreenSpot Pro29 percent—model author2026-10-07
author-reported TempCompass71.7 percent—model author2026-10-07

Use-case evidence

5 use cases

What it is good at 5 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 LLMs

Facts

Pipeline tagimage-text-to-text
Librarytransformers
ArchitecturesQwen2_5_VLForConditionalGeneration
Model typeqwen2_5_vl
Dtypebfloat16
Params by dtypeBF16: 8,292,166,656
Size bandM
MoEno
Context length128,000 (config.json max_position_embeddings)
PapersarXiv:2309.00071, arXiv:2409.12191, arXiv:2308.12966
LicenseApache 2.0 (apache-2.0)
Hub snapshot2026-10-25

Servability

vLLM · SGLang

Servability

vLLM: supported · Qwen2_5_VLForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen2_5_VLForConditionalGeneration · 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 Qwen2.5-VL-7B-Instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)20 GB · Single GPU (<24 GB)
FP8 (1 byte/param)10 GB · Single GPU (<24 GB)
INT4 (0.5 bytes/param)5.0 GB · Single GPU (<24 GB)

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

All variants

40 variants

Lineage

Original model Family: Qwen/Qwen2.5 1,781 derivatives on the Hub

quantized: 159finetune: 1,256adapter: 361merge: 5

Top variants (40 shown, ranked by downloads)

Relation
Quant
40 rows
Variant Relation Quant Params Band License Author Likes Downloads
Qwen/Qwen2.5-VL-7B-Instruct-AWQ quantized AWQ 8.29B M apache-2.0 Qwen 118 15.2M
allenai/olmOCR-2-7B-1025-FP8 quantized -FP8 8.29B M apache-2.0 allenai 257 5.3M
nvidia/Qwen2.5-VL-7B-Instruct-NVFP4 quantized NVFP4 5.03B M other nvidia 27 2.7M
numind/NuMarkdown-8B-Thinking finetune — 8.29B M mit numind 498 2.6M
reducto/RolmOCR finetune — 8.29B M apache-2.0 reducto 586 2.2M
unsloth/Qwen2.5-VL-7B-Instruct-GGUF quantized GGUF — — apache-2.0 unsloth 241 2M
allenai/olmOCR-7B-0825-FP8 quantized -FP8 8.29B M apache-2.0 allenai 10 935.2k
huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated finetune — 8.29B M apache-2.0 huihui-ai 61 776.2k
lmstudio-community/Qwen2.5-VL-7B-Instruct-GGUF quantized GGUF — — apache-2.0 lmstudio-community 11 748.7k
unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit quantized -bnb 8.29B M apache-2.0 unsloth 50 668.6k
xlangai/OpenCUA-7B finetune — 8.29B M mit xlangai 33 448.8k
RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic quantized -FP8 8.29B M apache-2.0 RedHatAI 5 444.1k
chancharikm/qwen2.5-vl-7b-cam-motion finetune — 8.29B M other chancharikm 18 407.1k
unsloth/Qwen2.5-VL-7B-Instruct-bnb-4bit quantized -bnb 8.50B M apache-2.0 unsloth 15 370.2k
unsloth/Qwen2.5-VL-7B-Instruct finetune — 8.29B M apache-2.0 unsloth 18 351.5k
typhoon-ai/typhoon-ocr-7b finetune — 8.29B M apache-2.0 typhoon-ai 82 309.7k
ggml-org/Qwen2.5-VL-7B-Instruct-GGUF quantized GGUF — — apache-2.0 ggml-org 19 235.1k
TianheWu/VisualQuality-R1-7B finetune — 8.29B M mit TianheWu 16 170.7k
nomic-ai/colnomic-embed-multimodal-7b adapter — — — apache-2.0 nomic-ai 108 159.8k
nomic-ai/nomic-embed-multimodal-7b adapter — — — apache-2.0 nomic-ai 50 162.4k
mradermacher/Qwen2.5-VL-7B-Instruct-GGUF quantized GGUF — — — mradermacher 6 140.5k
RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w8a8 quantized -quant 8.29B M apache-2.0 RedHatAI 9 135.8k
bartowski/Qwen_Qwen2.5-VL-7B-Instruct-GGUF quantized GGUF — — apache-2.0 bartowski 19 133.9k
allenai/olmOCR-7B-0725-FP8 quantized -FP8 8.29B M apache-2.0 allenai 18 125.7k
mlx-community/olmOCR-2-7B-1025-mlx-8bit quantized mlx — — apache-2.0 mlx-community 2 111.2k
TIGER-Lab/VL-Rethinker-7B finetune — 8.29B M apache-2.0 TIGER-Lab 15 110.2k
NOVAglow646/Monet-7B finetune — 8.29B M mit NOVAglow646 7 93.2k
TIGER-Lab/VideoScore2 finetune — 8.29B M apache-2.0 TIGER-Lab 5 70.2k
mlx-community/Qwen2.5-VL-7B-Instruct-4bit finetune -4bit 8.29B M apache-2.0 mlx-community 6 65.4k
yueliu1999/GuardReasoner-VL-7B finetune — 8.29B M apache-2.0 yueliu1999 4 59.3k
WSDW/Qwen2_CN_NSFW_GGUF quantized GGUF — — apache-2.0 WSDW 14 56.6k
Ertugrul/Qwen2.5-VL-7B-Captioner-Relaxed finetune — 8.29B M apache-2.0 Ertugrul 29 55.2k
RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w4a16 quantized -quant 8.34B M apache-2.0 RedHatAI 8 54.5k
Video-R1/Video-R1-7B finetune — 8.29B M apache-2.0 Video-R1 18 53.6k
allenai/olmOCR-7B-0825 finetune — 8.29B M apache-2.0 allenai 58 50.5k
Metric-AI/ColQwen2.5-7b-multilingual-v1.0 adapter — — — mit Metric-AI 16 51k
PatataAliena/Qwen2.5-VL-7B-Instruct-Q4_K_M-GGUF quantized GGUF — — apache-2.0 PatataAliena 4 51.3k
CodeGoat24/UnifiedReward-qwen-7b finetune — 8.29B M mit CodeGoat24 8 49.6k
Skywork/Skywork-VL-Reward-7B finetune — 8.29B M mit Skywork 48 47.6k
Hcompany/Holo1-7B finetune — 8.29B M apache-2.0 Hcompany 225 36.5k

Repository changelog

12 commits

Repository changelog 12 commits

DateCommitSHA
2025-04-06 Update tokenizer_config.json cc59489
2025-03-23 Update generation_config.json 5b5eecc
2025-03-21 Update generation_config.json b901af6
2025-03-06 Update preprocessor_config.json (#24) 68156fd
2025-02-15 Update preprocessor_config.json 6e6556e
2025-02-06 remove base_model (#1) c6adf13
2025-01-27 Update README.md 41bf8b5
2025-01-27 Update README.md 471456a
2025-01-27 Update README.md 57a7cc3
2025-01-27 Create README.md 244df9a
2025-01-26 Upload folder using huggingface_hub a22b9b2
2025-01-26 initial commit 1cd6578

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Qwen2.5-VL-7B-Instruct, 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
Featherless
hf
 Qwen/Qwen2.5-VL-7B-Instruct — — — — — — — live 2026-10-25

Articles and coverage

30 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.

Official4

Qwen2.5-VL-32B: Smarter and Lighter
qwenlm.github.io2025-03-24officialauthorityHN front pageabout the Qwen2.5 familyHN 544 pts · 293 comments606 words
Alibaba open-sourced Qwen2.5-VL-32B-Instruct under the Apache 2.0 license, optimizing the model with reinforcement learning to improve human alignment and mathematical reasoning. This 32B parameter model outperforms larger 72B predecessors on benchmarks like MM-MT-Bench and MMMU-Pro while maintaining top-tier pure text capabilities. The model operates within the paradigm of "fast thinking" to prioritize subjective experience and complex multi-step reasoning.written, reviewed, cited
  • The model achieves significant advantages in MMMU, MMMU-Pro, and MathVista benchmarks focusing on complex, multi-step reasoning.
  • Qwen2.5-VL-32B-Instruct outperforms its predecessor Qwen2-VL-72B-Instruct by a substantial margin on the MM-MT-Bench benchmark.
Qwen2.5: A Party of Foundation Models
qwenlm.github.io2024-09-18officialauthorityHN front pageabout the Qwen2.5 familyHN 168 pts · 38 comments1,744 words
Qwen2.5 introduces dense decoder-only models pretrained on up to 18 trillion tokens, available in sizes from 0.5B to 72B parameters. Most variants are licensed under Apache 2.0, excluding the 3B and 72B models, and support a 128K context window with 8K generation limits. Specialized versions for coding and mathematics offer enhanced performance on benchmarks like HumanEval and MATH.written, reviewed, cited
  • Qwen2.5-Coder-7B-Instruct outperforms many larger language models across a range of programming languages and tasks.
  • Qwen2.5-Math-72B-Instruct general performance surpasses both Qwen2-Math-72B-Instruct and GPT4-o.
Qwen2.5-VL-7B-Instruct
qwen.aiofficialauthority1,803 words
Qwen2.5-VL
qwenlm.github.io2025-01-27officialauthorityabout the Qwen2.5 familyHN 8 pts · 0 comments

Analysis6

Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphs
cinegraphs.ai2026-02-08HN front pageHN 101 pts · 20 comments
Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M
simonwillison.net2025-01-26authorityHN 98 pts · 2 comments627 words
Civic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt data
itsmeduncan.com2026-04-25HN 9 pts · 0 comments646 words
Qwen2.5-VL-32B: Smarter and Lighter
simonwillison.net2025-03-25authorityabout the Qwen2.5 familyHN 3 pts · 2 comments
Qwen2.5 Technical Report
arxiv.org2025-01-03authorityabout the Qwen2.5 family
Qwen2.5-VL: State-of-the-art multimodal LLM
github.com2025-01-30authorityabout the Qwen2.5 familyHN 3 pts · 0 comments
All coverage tracked for this model (30) — append-only, nothing is ever removed
TitleSourcePublishedFirst seenSignals
Qwen2.5-VL-7B-Instructqwen.ai official—2026-10-07exa
Qwen2.5-VL: Architecture, Data, Benchmarks and Inferencedebuggercafe.com—2026-10-07exa
Qwen2.5-VL-7B-Instruct by Qwen - Overview, Benchmarks & Hardware | Q4KM.aiq4km.ai—2026-10-07exa
Qwen2.5-VL-7B: 7B Vision-Language Modelemergentmind.com—2026-10-07exa
kev: Jev-like model built on Qwen2.5-0.5Bgithub.com2026-09-192026-10-07hn
Civic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt dataitsmeduncan.com2026-04-252026-10-07hn
Show HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphscinegraphs.ai2026-02-082026-10-07hn
Qwen2.5-Omni Technical Reporthuggingface.co2025-03-302026-10-07hn
Alibaba Qwen2.5-Omni-7B: Open Source End-to-End Multimodal AI Modelalizila.com2025-03-272026-10-07hn
Qwen2.5 Omni: See, Hear, Talk, Write, Do It Allqwenlm.github.io official2025-03-262026-10-07hn
Qwen2.5-VL-32B: Smarter and Lightersimonwillison.net2025-03-252026-10-07hn
Qwen2.5-VL-32B: Smarter and Lighterqwenlm.github.io official2025-03-242026-10-07hn
Qwen2.5-Pluschat.qwenlm.ai2025-01-312026-10-07hn
Qwen2.5-VL: State-of-the-art multimodal LLMgithub.com2025-01-302026-10-07hn
Qwen2.5-Max: The Next Leap in AI Innovationmedium.com2025-01-292026-10-07hn
New Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarkstwitter.com2025-01-282026-10-07hn
Qwen2.5-Max: Exploring the intelligence of large-scale MoE modelqwenlm.github.io official2025-01-282026-10-07hn
Show HN: I made a free study tool powered by Qwen2.5freeflashcardgenerator.com2025-01-282026-10-07hn
Qwen2.5-VLqwenlm.github.io official2025-01-272026-10-07hn, exa
Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1Msimonwillison.net2025-01-262026-10-07hn
Qwen2.5-1M: Deploy your own Qwen with context length up to 1M tokensqwenlm.github.io official2025-01-262026-10-07hn
Qwen2.5 Technical Reportarxiv.org2025-01-032026-10-07exa
Qwen2.5-coder on the events occurring during the Tiananmen Square protestsnews.ycombinator.com2024-11-202026-10-07hn
Qwen2.5-Coder-32B is an LLM that can code well that runs on my Macsimonwillison.net2024-11-132026-10-07hn
Qwen2.5-Coder Technical Reportarxiv.org2024-11-112026-10-07hn
Qwen2.5 Coderollama.com2024-11-112026-10-07hn
Qwen2.5-Coder Beats GPT-4o and Claude 3.5 Sonnet in Codingqwenlm.github.io official2024-11-112026-10-07hn
Qwen2.5-Coder-32B with coding abilities matching those of GPT-4ogithub.com2024-11-092026-10-07hn
Guide how to use a local LLM Qwen2.5-coder-7B as an autocompelte in VSCodeeamag.me2024-10-292026-10-07hn
Qwen2.5: A Party of Foundation Modelsqwenlm.github.io official2024-09-182026-10-07hn

Papers

3 papers

Papers 3

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

  • Qwen3-VL-8B-Instruct · 8.77B
    same size band (M), same task (image-text-to-text), more providers, permissive license
  • Qwen3.5-9B · 9.65B
    same task (image-text-to-text), more providers, permissive license
  • UI-TARS-1.5-7B · 8.29B
    same size band (M), same task (image-text-to-text), more providers, permissive license

Sources

3 sources

Sources

Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:32 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:00 UTC · Last verified 2026-10-25

Follow Qwen2.5-VL-7B-Instruct

Watch this model

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