Models catalog

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

Qwen 2.5 0.5B

Model size

676.00 MB

Parameters

5 million

Quantization

Q8_0

Languages

🇬🇧 🇨🇳
3+

License

Apache 2.0

More info

Click here

Llama 3.2 1B

Model size

1.09 GB

Parameters

1 billion

Quantization

Q6_K_L

Languages

🇬🇧 🇫🇷
6+

License

llama3.2

More info

Click here

Qwen 2.5 1.5B

Model size

1.89 GB

Parameters

1 billion

Quantization

Q8_0

Languages

🇬🇧 🇨🇳
3+

License

Apache 2.0

More info

Click here

Gemma 2 2B

Model size

2.15 GB

Parameters

2 billion

Quantization

Q6_K

Languages

🇬🇧

License

gemma

More info

Click here

Llama 3.2 3B

Model size

2.74 GB

Parameters

3 billion

Quantization

Q6_K_L

Languages

🇬🇧 🇫🇷
6+

License

llama3.2

More info

Click here

Phi 3.5 mini

Model size

3.14 GB

Parameters

3 billion

Quantization

Q6_K

Languages

🇬🇧

License

MIT

More info

Click here

Qwen 2.5 7B

Model size

6.25 GB

Parameters

7 billion

Quantization

Q6_K

Languages

🇬🇧 🇨🇳
3+

License

Apache 2.0

More info

Click here

Mistral 7B v0.2

Model size

5.94 GB

Parameters

7 billion

Quantization

Q6_K

Languages

🇬🇧 🇫🇷
4+

License

Apache 2.0

More info

Click here

DeepSeek R1 (Qwen 7B)

Model size

6.25 GB

Parameters

7 billion

Quantization

Q6_K

Languages

🇨🇳 🇬🇧

License

MIT

More info

Click here

LLaMA 3.1 8B

Model size

6.60 GB

Parameters

8 billion

Quantization

Q6_K

Languages

🇬🇧 🇫🇷
6+

License

llama3.1

More info

Click here

Granite 3.1 8B

Model size

6.71 GB

Parameters

8 billion

Quantization

Q6_K

Languages

🇬🇧 🇫🇷
9+

License

Apache 2.0

More info

Click here

DeepSeek R1 (Llama 8B)

Model size

6.60 GB

Parameters

8 billion

Quantization

Q6_K

Languages

🇨🇳 🇬🇧

License

MIT

More info

Click here

Gemma 2 9B

Model size

7.59 GB

Parameters

9 billion

Quantization

Q6_K

Languages

🇬🇧

License

gemma

More info

Click here

Mistral NeMo 2407

Model size

10.10 GB

Parameters

12 billion

Quantization

Q6_K

Languages

🇬🇧 🇫🇷
7+

License

Apache 2.0

More info

Click here

Qwen 2.5 14B

Model size

12.10 GB

Parameters

14 billion

Quantization

Q6_K

Languages

🇬🇧 🇨🇳
3+

License

Apache 2.0

More info

Click here

Phi 4

Model size

12.00 GB

Parameters

14 billion

Quantization

Q6_K

Languages

🇬🇧

License

MIT

More info

Click here

DeepSeek R1 (Qwen 14B)

Model size

12.10 GB

Parameters

14 billion

Quantization

Q6_K

Languages

🇨🇳 🇬🇧

License

MIT

More info

Click here

Gemma 2 27B

Model size

22.30 GB

Parameters

27 billion

Quantization

Q6_K

Languages

🇬🇧

License

gemma

More info

Click here

Qwen 2.5 32B

Model size

26.90 GB

Parameters

32 billion

Quantization

Q6_K

Languages

🇬🇧 🇨🇳
3+

License

Apache 2.0

More info

Click here

DeepSeek R1 (Qwen 32B)

Model size

26.90 GB

Parameters

32 billion

Quantization

Q6_K

Languages

🇨🇳 🇬🇧

License

MIT

More info

Click here

QwQ 32B

Model size

26.90 GB

Parameters

32 billion

Quantization

Q6_K

Languages

🇨🇳 🇬🇧

License

Apache 2.0

More info

Click here

Ready for faster, safer and cheaper writing?

Subscribe to our newsletter and stay updated.

Gems Platforms, Inc. | © Copyright 2025 | All rights reserved