GGUF models: lgpl-3.0 license

3 GGUF models listed under the lgpl-3.0 license on Hugging Face. Always read the license text before commercial use. Sizes run from 124M to 13.2B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
SU
SunlightV2 0.8B
Sunlightv · CaptchaKraken
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
MI
MidnightV2 4B
Midnightv · CaptchaKraken
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
BI
BigTranslate 13b
Bigtranslate · AliciaTestarossa
Params13.2B
Context2K
Smallest5.0 GB
GGUF
QW
Qwen3 4B Instruct 2507
Qwen · mrankitvish577
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
OR
Orkigpt Full3
Orkigpt · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
GGUF

About the lgpl-3.0 license

The license text is in the model repository on Hugging Face. Licenses can differ between a quantized file and the original model, so check both.

3 GGUF models are listed under lgpl-3.0 on Hugging Face. The most downloaded are SunlightV2 0.8B, MidnightV2 4B and BigTranslate 13b. This is information, not legal advice: always read the license in the repository before you use a model commercially.

Frequently asked questions

Can I use lgpl-3.0 GGUF models commercially?

The license text is in the model repository on Hugging Face. Licenses can differ between a quantized file and the original model, so check both. Check the license text in the repository and the license of the base model before you build a product on it.

Keep browsing