Models catalog

A curated list of open source LLMs you can install on your laptop to help you write

Find out the best LLM for your Mac →

Qwen 3 4B 2507

Model size

2.50 GB

Parameters

4 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷7+

License

Apache 2.0

More info

Click here

Writing Partner Mistral 7B

Model size

4.37 GB

Parameters

7 billion

Quantization

Q4_K_M

Languages

🇬🇧

License

Apache 2.0

More info

Click here

LLaMA 3.1 8B

Model size

4.92 GB

Parameters

8 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷6+

License

llama3.1

More info

Click here

Qwen 3 8B

Model size

5.03 GB

Parameters

8 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷7+

License

Apache 2.0

More info

Click here

Gemma 3n E4B

Model size

4.24 GB

Parameters

8 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷7+

License

gemma

More info

Click here

Mistral NeMo 2407

Model size

7.48 GB

Parameters

12 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷7+

License

Apache 2.0

More info

Click here

Gemma 3 12B

Model size

7.30 GB

Parameters

12 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷7+

License

gemma

More info

Click here

Phi 4

Model size

9.05 GB

Parameters

14 billion

Quantization

Q4_K_M

Languages

🇬🇧

License

MIT

More info

Click here

Qwen 3 14B

Model size

9.00 GB

Parameters

14 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷7+

License

Apache 2.0

More info

Click here

gpt-oss 20B

Model size

12.10 GB

Parameters

20 billion

Quantization

MXFP4

Languages

🇬🇧

License

Apache 2.0

More info

Click here

Gemma 3 27B

Model size

16.50 GB

Parameters

27 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷7+

License

gemma

More info

Click here

Qwen 3 30B A3B 2507

Model size

18.60 GB

Parameters

30 billion

Quantization

Q4_K_M

Languages

🇬🇧 🇫🇷7+

License

Apache 2.0

More info

Click here

QwQ 32B

Model size

19.90 GB

Parameters

32 billion

Quantization

Q4_K_M

Languages

🇨🇳 🇬🇧

License

Apache 2.0

More info

Click here