Skip to content
Pearl Compute

Model licences

Pearl Compute serves open-weight models. Each model's licence and its attribution are below; your use of a model is subject to its licence.

Llama 3.1 8B Instruct

Offered

Built with Llama. Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc.

Licence
Llama 3.1 Community License
Weights we run
pearl-ai/Llama-3.1-8B-Instruct-pearl
Based on
meta-llama/Llama-3.1-8B-Instruct

Gemma 4 31B IT

In validation

Gemma 4 is released by Google under the Apache License 2.0; use is also subject to the Gemma Prohibited Use Policy. Pearl quantization by Pearl Research Labs.

Licence
Apache-2.0
Weights we run
pearl-ai/Gemma-4-31B-it-pearl
Based on
google/gemma-4-31b-it

Qwen3 30B A3B Instruct 2507

Not offered yet

Qwen3 by Alibaba Cloud (Apache-2.0); Pearl quantization by Pearl Research Labs.

Licence
Apache-2.0
Weights we run
pearl-ai/Qwen3-30B-A3B-Instruct-2507-pearl
Based on
Qwen/Qwen3-30B-A3B-Instruct-2507

Llama 3.3 70B Instruct

Not offered yet

Built with Llama. Llama 3.3 is licensed under the Llama 3.3 Community License, Copyright © Meta Platforms, Inc.

Licence
Llama 3.3 Community License
Weights we run
pearl-ai/Llama-3.3-70B-Instruct-pearl
Based on
meta-llama/Llama-3.3-70B-Instruct