OpenHubAI
Community model & dataset hub

Stop renting intelligence.

Run models on hardware you control. No API key, no per-token bill, no cloud dependency. Structured reviews and enforced documentation are how you tell which ones are actually worth running.

Start with the task
Text generationVision-languageOtherEmbeddingsSpeech recognitionFill-maskText classificationImage classification

200 models · All tasks · All licences

Highest ratedMost reviewedNewest
Cards List
Rank by dimensionAccuracyFine-tuneDocsSpeed
Embeddingsapache-2.0
sentence-transformers/all-MiniLM-L6-v2
Good for making your own site search or FAQ matching work by meaning instead of exact keywords. Not a chatbot on its own and needs your own documents to be useful.
Accuracy4.4
Fine-tune4.5
Docs4.2
Speed4.9
4.5/ 5 · 3 reviews
254.0M
Text generationapache-2.0
Qwen/Qwen2.5-7B-Instruct
Good for drafting HTML, CSS, and JavaScript snippets and explaining how they work. Not reliable for security sensitive code such as authentication or payment handling without human review.
Accuracy4.1
Fine-tune4.2
Docs4.0
Speed3.8
4.0/ 5 · 3 reviews
10.2M
Text generationapache-2.0
unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
Good for writing and refactoring code across common languages and explaining unfamiliar codebases. Still makes mistakes on edge cases, so treat its output as a draft that needs review, not a ready merge.
Accuracy4.5
Fine-tune3.9
Docs3.8
Speed3.1
3.8/ 5 · 4 reviews
12.8M
Text generationllama3.2
meta-llama/Llama-3.2-1B-Instruct
Good for a lightweight customer chat assistant that answers common questions from a script you provide. Not reliable outside that script, and it should not make refund or account decisions on its own.
Accuracy3.5
Fine-tune3.8
Docs3.3
Speed4.6
3.8/ 5 · 4 reviews
6.2M
Text generationapache-2.0
openai/gpt-oss-20b
Good for triaging log lines and alerts into plain English summaries so a person can prioritise faster. Not a substitute for a real detection pipeline, and it should never auto close an alert on its own.
Accuracy4.1
Fine-tune3.5
Docs3.7
Speed3.4
3.7/ 5 · 3 reviews
6.6M
Text generationapache-2.0
Qwen/Qwen2.5-0.5B-Instruct
Good for a fast, on-device assistant for short replies and simple instructions. Too small for long documents or complex reasoning, and it will make things up under pressure.
Accuracy3.0
Fine-tune3.3
Docs3.3
Speed4.9
3.6/ 5 · 3 reviews
7.0M
Text generationllama3.1
meta-llama/Llama-3.1-8B-Instruct
Good for summarising general contracts and explaining common UK legal terms in plain English. Has no specialist UK legal training, so treat it as a starting point only, never as legal advice, and confirm with a solicitor.
Accuracy3.6
Fine-tune3.8
Docs3.5
Speed3.6
3.6/ 5 · 3 reviews
5.6M
Text generationapache-2.0
Qwen/Qwen2.5-1.5B-Instruct
Good for a quick first read of US style contracts and flagging clauses worth a closer look. Has no specialist US legal training, so it is not a substitute for a licensed attorney and should not be used for filings.
Accuracy3.2
Fine-tune3.3
Docs3.4
Speed4.3
3.5/ 5 · 3 reviews
7.3M
Text generationapache-2.0
farbodtavakkoli/OTel-2.0-LLM-31B-IT
Good for explaining accounting terms and drafting first pass budget summaries from numbers you provide. Has no professional finance training, so do not use it for tax filings or investment decisions without a qualified accountant.
Accuracy3.5
Fine-tune3.5
Docs3.2
Speed3.1
3.3/ 5 · 3 reviews
7.2M
Text rankingapache-2.0
cross-encoder/ms-marco-MiniLM-L6-v2
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
87.6M
Embeddingsmit
BAAI/bge-small-en-v1.5
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
64.6M
Otherapache-2.0
google/electra-base-discriminator
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
59.3M
Fill-maskapache-2.0
google-bert/bert-base-uncased
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
47.2M
Embeddingsapache-2.0
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
46.4M
Embeddingsmit
BAAI/bge-m3
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
37.8M
Translationapache-2.0
google-t5/t5-small
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
24.3M
Embeddingsapache-2.0
sentence-transformers/all-mpnet-base-v2
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
24.1M
Time seriesapache-2.0
amazon/chronos-2
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
23.1M
Fill-maskmit
FacebookAI/xlm-roberta-base
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
21.8M
Image classification—
openai/clip-vit-base-patch32
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
21.2M
Text generationapache-2.0
Qwen/Qwen3-0.6B
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
21.0M
Otherother
Comfy-Org/MiniMax-H3
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
18.8M
Text generation—
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
18.6M
Text classificationapache-2.0
BAAI/bge-reranker-v2-m3
Documentation incomplete. Claimed by no publisher yet.
Accuracy—
Fine-tune—
Docs—
Speed—
—/ 5 · 0 reviews
18.2M