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-32B-Instruct

Hugging Face ↗ Follow changes

Qwen Apache 2.0 out 19 months ago

33.5B parameters, images and text in, text out, 125K tokens of context. 1 provider serves it.

Verified 2026-10-25 Rank #108 in LLMs · score 98.4 method v1 Sources 3 Downloads 30d 827.9k · #128 of 619 tracked

Can I run it?20GB at INT4Estimatefits a 24 GB cardmethod
Can I use it?Apache 2.0Permissive; patent grantlicence file2026-10-24
Do people use it?827.9kdownloads, 30 days#128 of 619 we track · top 21%+2 likes, downloads +4% this week507 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.

25 best of 30 tracked

The 2 picks above, plus these 23. 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-VL-32B: Smarter and Lighterqwenlm.github.io · 2025-03-24 · 544 HN pts · official
  3. ArticleQwen2.5-1M: Deploy your own Qwen with context length up to 1M tokensqwenlm.github.io · 2025-01-26 · official
  4. ArticleQwen2.5: A Party of Foundation Modelsqwenlm.github.io · 2024-09-18 · 168 HN pts · official
  5. ArticleQwen2.5-Max: Exploring the intelligence of large-scale MoE modelqwenlm.github.io · 2025-01-28 · official
  6. ArticleQwen2.5-VL-32B: Smarter and Lighterqwen.ai · undated · official
  7. ArticleQwen2.5-Coder-32B is an LLM that can code well that runs on my Macsimonwillison.net · 2024-11-13
  8. ArticleShow HN: Fine-tuned Qwen2.5-7B on 100 films for probabilistic story graphscinegraphs.ai · 2026-02-08
  9. ArticleQwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1Msimonwillison.net · 2025-01-26
  10. ArticleQwen2.5-Coder Beats GPT-4o and Claude 3.5 Sonnet in Codingqwenlm.github.io · 2024-11-11 · official
  11. ArticleCivic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt dataitsmeduncan.com · 2026-04-25
  12. ArticleQwen2.5-VLqwenlm.github.io · 2025-01-27 · 8 HN pts · official
  13. CodeQwen2.5-Coder-32B with coding abilities matching those of GPT-4ogithub.com · 2024-11-09
  14. ArticleQwen2.5 Omni: See, Hear, Talk, Write, Do It Allqwenlm.github.io · 2025-03-26 · official
  15. ArticleAlibaba Qwen2.5-Omni-7B: Open Source End-to-End Multimodal AI Modelalizila.com · 2025-03-27
  16. ArticleQwen2.5-Max: The Next Leap in AI Innovationmedium.com · 2025-01-29
  17. ArticleQwen2.5-Omni Technical Reporthuggingface.co · 2025-03-30
  18. PaperQwen2.5-Coder Technical Reportarxiv.org · 2024-11-11
  19. DiscussionQwen2.5-coder on the events occurring during the Tiananmen Square protestsnews.ycombinator.com · 2024-11-20
  20. PaperQwen2.5 Technical Reportarxiv.org · 2025-01-03
  21. CodeQwen2.5-VL: State-of-the-art multimodal LLMgithub.com · 2025-01-30 · 3 HN pts
  22. DiscussionNew Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarkstwitter.com · 2025-01-28
  23. ArticleQwen2.5-VL: Architecture, Data, Benchmarks and Inferencedebuggercafe.com · 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; 30 quantized builds for local use; a big base for builders (85 fine-tunes, adapters and merges).

  • As a service1Featherless
  • On own hardware30quantized builds
  • Built on8573 fine-tunes · 9 adapters · 3 merges
  • In apps100+Hugging Face Spaces

Top Spaces running it: hadadrjt/ai ♥ 86 · dmorawiec/Qwen-VL-Object-Detection ♥ 18 · jairwaal/image ♥ 16 · ariG23498/qwen-od ♥ 15

Will it fit?

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

Fits a 64 GB Mac (unified memory) at INT4

About 20 GB at INT4, 40 GB at FP8, 80 GB at BF16: weights only, so leave room for the KV cache.

16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 20 GB of weights (estimate; KV cache and activations extra)INT420 GBFP8: about 40 GB of weights (estimate; KV cache and activations extra)FP840 GBBF16: about 80 GB of weights (estimate; KV cache and activations extra)BF1680 GB
16 GB card64 GB Mac2×80 GB8×80 GBINT4: about 20 GB of weights (estimate; KV cache and activations extra)INT420 GBFP8: about 40 GB of weights (estimate; KV cache and activations extra)FP840 GBBF16: about 80 GB of weights (estimate; KV cache and activations extra)BF1680 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 (2025-03-21), amber triangles are 6 dated articles (each links to it), grey ticks are repo commits.

OctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2025-04-14: 1 repo commit2025-04-06: 1 repo commit2025-03-26: 1 repo commit2025-03-25: 1 repo commit2025-03-24: 2 repo commits2025-03-23: 1 repo commit2025-03-21: 4 repo commitsQwen2.5-VL-32B: Smarter and Lighter · 2025-03-24Qwen2.5: A Party of Foundation Models · 2024-09-18Qwen2.5-VL · 2025-01-27Qwen2.5-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 2025-03-21 · 2025-03-21Weights 2025-03-21now · 1 provider
OctNovDecJanFebMarAprMayJunJulAugSepOctNovDecJanFebMarAprMayJunJulAugSepOct2025-04-14: 1 repo commit2025-04-06: 1 repo commit2025-03-26: 1 repo commit2025-03-25: 1 repo commit2025-03-24: 2 repo commits2025-03-23: 1 repo commit2025-03-21: 4 repo commitsQwen2.5-VL-32B: Smarter and Lighter · 2025-03-24Qwen2.5: A Party of Foundation Models · 2024-09-18Qwen2.5-VL · 2025-01-27Qwen2.5-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 2025-03-21 · 2025-03-21Weights 2025-03-21now · 1 provider

What people built on it

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

115 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.

30 quantized (Hugging Face model tree)73 fine-tunes (Hugging Face model tree)3 merges (Hugging Face model tree)9 adapters (Hugging Face model tree)30 quantized73 fine-tunes3 merges9 adapters
30 quantized (Hugging Face model tree)73 fine-tunes (Hugging Face model tree)3 merges (Hugging Face model tree)9 adapters (Hugging Face model tree)30 quantized73 fine-tunes3 merges9 adapters
GGUF bartowski/Qwen_Qwen2.5-VL-32B-Instruct-GGUF for llama.cpp, Ollama, LM Studio 406.5k downloads MLX AITRADER/Qwen2.5-VL-32B-Instruct-abliterated-mlx-8bit for Apple silicon 1.4k downloads AWQ Qwen/Qwen2.5-VL-32B-Instruct-AWQ for vLLM, SGLang 5.5M downloads

All variants →

Reference

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

Benchmarks

25 rows

Benchmarks 25 rows

measured third-party leaderboard rowauthor-reported number from the model card or eval files (25)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 AITZ83.1—model author2026-10-07
author-reported Android Control69.6/93.3—model author2026-10-07
author-reported AndroidWorld22—model author2026-10-07
author-reported CC-OCR · Extract text from documents77.1—model author2026-10-07
author-reported CharadesSTA54.2—model author2026-10-07
author-reported DocVQA · Extract text from documents94.8—model author2026-10-07
author-reported GPQA Diamond · Reason through hard problems46Qwen2.5-VL-32Bmodel author2026-10-07
author-reported HumanEval · Write code with agents91.5Qwen2.5-VL-32Bmodel author2026-10-07
author-reported InfoVQA · Extract text from documents83.4—model author2026-10-07
author-reported LVBench · Understand images and video49—model author2026-10-07
author-reported MATH-500 · Reason through hard problems82.2Qwen2.5-VL-32Bmodel author2026-10-07
author-reported MBPP · Write code with agents84Qwen2.5-VL-32Bmodel author2026-10-07
author-reported MMBench · Understand images and video1.93—model author2026-10-07
author-reported MMLU · Reason through hard problems78.4Qwen2.5-VL-32Bmodel author2026-10-07
author-reported MMLU-Pro · Reason through hard problems68.8Qwen2.5-VL-32Bmodel author2026-10-07
author-reported MMMU · Understand images and video70—model author2026-10-07
author-reported MMMU-Pro · Understand images and video49.5—model author2026-10-07
author-reported MMStar · Understand images and video69.5—model author2026-10-07
author-reported MathVision · Understand images and video40—model author2026-10-07
author-reported MathVista · Understand images and video74.7—model author2026-10-07
author-reported OCRBench · Extract text from documents57.2/59.1—model author2026-10-07
author-reported OSWorld5.92—model author2026-10-07
author-reported ScreenSpot88.5—model author2026-10-07
author-reported ScreenSpot Pro39.4—model author2026-10-07
author-reported Video-MME · Understand images and video70.5/77.9—model author2026-10-07

What the card says

1 cited sentence

Summary generated, cited

It is designed for tasks such as analyzing charts, layouts, and long videos.[1]

  1. “analyzing texts, charts, icons, graphics, and layouts wit…”

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

6 use cases

What it is good at 6 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 LLMs

Facts

Pipeline tagimage-text-to-text
Librarytransformers
ArchitecturesQwen2_5_VLForConditionalGeneration
Model typeqwen2_5_vl
Dtypebfloat16
Params by dtypeBF16: 32,763,876,352 · F32: 688,841,984
Size bandL
MoEno
Context length128,000 (config.json max_position_embeddings)
Languagesen
PapersarXiv:2309.00071, arXiv:2502.13923
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-32B-Instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.

BF16 (2 bytes/param)80 GB · Multi-GPU node (<640 GB)
FP8 (1 byte/param)40 GB · Single high-end GPU (<80 GB)
INT4 (0.5 bytes/param)20 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/Qwen2.5 115 derivatives on the Hub

quantized: 30finetune: 73merge: 3adapter: 9

Top variants (40 shown, ranked by downloads)

Relation
Quant
40 rows
Variant Relation Quant Params Band License Author Likes Downloads
Qwen/Qwen2.5-VL-32B-Instruct-AWQ quantized AWQ 33.5B L apache-2.0 Qwen 77 5.5M
bartowski/Qwen_Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — apache-2.0 bartowski 8 406.5k
BCCard/Qwen2.5-VL-32B-Instruct-FP8-Dynamic quantized -FP8 33.5B L apache-2.0 BCCard 5 287.1k
unsloth/Qwen2.5-VL-32B-Instruct finetune — 33.5B L apache-2.0 unsloth 1 115.5k
unsloth/Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — apache-2.0 unsloth 10 75.2k
lmstudio-community/Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — apache-2.0 lmstudio-community 1 70.5k
unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit quantized -bnb 34.3B L apache-2.0 unsloth 14 56.9k
unsloth/Qwen2.5-VL-32B-Instruct-bnb-4bit quantized -bnb 34.5B L apache-2.0 unsloth 4 54.9k
ggml-org/Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — apache-2.0 ggml-org 5 47.3k
DevQuasar-6/Qwen.Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — — DevQuasar-6 1 38.8k
samgreen/Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — apache-2.0 samgreen 6 37.1k
openfree/Qwen2.5-VL-32B-Instruct-Q4_K_M-GGUF quantized GGUF — — apache-2.0 openfree 113 15.2k
mradermacher/Qwen2.5-VL-32B-Instruct-i1-GGUF quantized GGUF — — apache-2.0 mradermacher 1 16.4k
karakuri-ai/karakuri-vl-32b-instruct-2507 finetune — 33.5B L apache-2.0 karakuri-ai 7 15.7k
CodeGoat24/UnifiedReward-qwen-32b finetune — 33.5B L mit CodeGoat24 1 14.7k
second-state/Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — apache-2.0 second-state 0 11.3k
xlangai/OpenCUA-32B finetune — 33.5B L mit xlangai 29 9.4k
openfree/Qwen2.5-VL-32B-Instruct-Q8_0-GGUF quantized Q8_0 — — apache-2.0 openfree 109 3.8k
gaianet/Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — apache-2.0 gaianet 0 7.4k
mPLUG/GUI-Owl-32B finetune — 33.5B L mit mPLUG 29 5.8k
leon-se/Qwen2.5-VL-32B-Instruct-FP8-Dynamic quantized -FP8 33.5B L apache-2.0 leon-se 1 6.9k
mradermacher/Qwen2.5-VL-32B-Instruct-GGUF quantized GGUF — — apache-2.0 mradermacher 2 5.2k
PromptEnhancer/PromptEnhancer-32B finetune — 33.5B L other PromptEnhancer 20 3.7k
zeromodels/qwen2.5-vl-32b-instruct finetune — — — apache-2.0 zeromodels 0 3.2k
OpenGVLab/ScaleCUA-32B finetune — 33.5B L apache-2.0 OpenGVLab 22 1.6k
ddvd233/QoQ-Med-VL-32B finetune — 33.5B L mit ddvd233 3 1.3k
One-RL-to-See-Them-All/Orsta-32B-0321 finetune — 33.5B L mit One-RL-to-See-Them-All 3 1.3k
PromptEnhancer/PromptEnhancer-Img2img-Edit finetune — 33.5B L other PromptEnhancer 10 920
AITRADER/Qwen2.5-VL-32B-Instruct-abliterated-mlx-8bit quantized mlx 33.5B L apache-2.0 AITRADER 0 1.4k
stockmark/Stockmark-DocReasoner-Qwen2.5-VL-32B finetune — 33.5B L apache-2.0 stockmark 0 1.2k
CodeGoat24/UnifiedReward-2.0-qwen-32b finetune — 33.5B L mit CodeGoat24 0 1.2k
litmudoc/Qwen2.5-VL-32B-Instruct-abliterated-MLX-Q8 finetune MLX — — apache-2.0 litmudoc 0 1.2k
AITRADER/Qwen2.5-VL-32B-Instruct-abliterated-mlx-fp16 finetune mlx 33.5B L apache-2.0 AITRADER 0 1.1k
One-RL-to-See-Them-All/Orsta-32B-0326 finetune — 33.5B L mit One-RL-to-See-Them-All 9 674
etri-vilab/SafeQwen2.5-VL-32B finetune — 33.5B L apache-2.0 etri-vilab 3 792
xiongwen/Qwen2.5-VL-32B-Instruct-Q4_K_M-GGUF quantized GGUF — — apache-2.0 xiongwen 0 856
UCSC-VLAA/MedVLThinker-32B-RL_m23k finetune — 33.5B L apache-2.0 UCSC-VLAA 1 718
leon-se/Qwen2.5-VL-32B-Instruct-W4A16-G128 quantized -W4A16 33.7B L apache-2.0 leon-se 2 606
prithivMLmods/Qwen2.5-VL-32B-Instruct-Unredacted-MAX finetune — 33.5B L apache-2.0 prithivMLmods 4 488
Tongyi-MiA/UI-Ins-32B finetune — 33.5B L cc-by-nc-sa-4.0 Tongyi-MiA 6 353

Repository changelog

11 commits

Repository changelog 11 commits

DateCommitSHA
2025-04-14 Update README.md (#11) 7cfb30d
2025-04-06 Update tokenizer_config.json 60bc26b
2025-03-26 Update model.safetensors.index.json 6bcf1c9
2025-03-25 Upload folder using huggingface_hub 97b6327
2025-03-24 Update README.md 9894855
2025-03-24 Update README.md d627b34
2025-03-23 Update generation_config.json 4af344b
2025-03-21 Update README.md 8b733ed
2025-03-21 Create README.md 6b3a2e6
2025-03-21 Upload folder using huggingface_hub 3a4ceb4
2025-03-21 initial commit 760f385

All providers

1 provider · 1 endpoint

Where to run 1 providers · 1 endpoints

Hosted endpoints observed for Qwen2.5-VL-32B-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-32B-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-32B: Smarter and Lighter
qwen.aiofficialauthorityabout the Qwen2.5 family74 words
Qwen2.5-VL
qwenlm.github.io2025-01-27officialauthorityabout the Qwen2.5 familyHN 8 pts · 0 comments

Analysis6

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
Qwen2.5-VL: Architecture, Data, Benchmarks and Inference
debuggercafe.comabout the Qwen2.5 family
Qwen2.5 VL 32B Instruct: benchmarks — ModelCap #120
modelcap.ai
Qwen : Qwen 2.5 VL 32B Instruct
ai-stats.phaseo.app
All coverage tracked for this model (30) — append-only, nothing is ever removed
TitleSourcePublishedFirst seenSignals
Qwen2.5-VL-32B: Smarter and Lighterqwen.ai official—2026-10-07exa
Qwen2.5-VL: Architecture, Data, Benchmarks and Inferencedebuggercafe.com—2026-10-07exa
Qwen2.5 VL 32B Instruct: benchmarks — ModelCap #120modelcap.ai—2026-10-07exa
Qwen : Qwen 2.5 VL 32B Instructai-stats.phaseo.app—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, exa
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
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

2 papers

Papers 2

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

  • gemma-4-31B-it · 31.3B
    same size band (L), same task (image-text-to-text), more providers, permissive license
  • Qwen3.8-27B · 27.8B
    same size band (L), same task (image-text-to-text), more providers, permissive license
  • Qwen3-VL-32B-Instruct · 33.4B
    same size band (L), same task (image-text-to-text), 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 Qwen2.5-VL-32B-Instruct

Watch this model

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