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.

31 models · Text generation · All licences · runs in SGLang

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.

Text generationapache-2.0
4.0
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.

Text generationllama3.2
3.8
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.

Text generationapache-2.0
3.7
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.

Text generationapache-2.0
3.6
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.

Text generationllama3.1
3.6
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.

Text generationapache-2.0
3.5
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.

Text generationapache-2.0
3.3
Qwen/Qwen3-0.6B

Documentation incomplete.

Text generationapache-2.0
trl-internal-testing/tiny-Qwen2ForCausalLM-2.5

Documentation incomplete.

Text generation
openai-community/gpt2

Documentation incomplete.

Text generationmit
Qwen/Qwen3-8B

Documentation incomplete.

Text generationapache-2.0
nvidia/Qwen3.6-35B-A3B-NVFP4

Documentation incomplete.

Text generationapache-2.0
Qwen/Qwen3-4B

Documentation incomplete.

Text generationapache-2.0
Qwen/Qwen2.5-3B-Instruct

Documentation incomplete.

Text generationother
openai/gpt-oss-120b

Documentation incomplete.

Text generationapache-2.0
Qwen/Qwen3-32B

Documentation incomplete.

Text generationapache-2.0
dphn/dolphin-2.9.1-yi-1.5-34b

Documentation incomplete.

Text generationapache-2.0
deepseek-ai/DeepSeek-V4-Flash-0731

Documentation incomplete.

Text generationmit
Qwen/Qwen-72B

Documentation incomplete.

Text generationother
Qwen/Qwen3-4B-Instruct-2507

Documentation incomplete.

Text generationapache-2.0
Qwen/Qwen2.5-7B-Instruct-AWQ

Documentation incomplete.

Text generationapache-2.0
nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16

Documentation incomplete.

Text generationother
Qwen/Qwen3-1.7B

Documentation incomplete.

Text generationapache-2.0
EleutherAI/pythia-160m

Documentation incomplete.

Text generationapache-2.0