← Back to Models
Qwen3
Qwen3 is the latest series of large language models from Alibaba Cloud. They are Transformer-based models with SwiGLU activation, attention QKV bias, and group query attention. They have strong performance in language understanding, generation, multilingual capabilities, coding, mathematics, and reasoning.
qwen3-0.6b
0.6B parameters
Base
Pull this model
Use the following command with the HoML CLI:
homl pull qwen3:0.6bResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 1.2 GB | 1.2 GB |
qwen3-1.7b
1.7B parameters
Base
Pull this model
Use the following command with the HoML CLI:
homl pull qwen3:1.7bResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 3.4 GB | 3.4 GB |
qwen3-4b
4B parameters
Base
Pull this model
Use the following command with the HoML CLI:
homl pull qwen3:4bResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 8 GB | 8 GB |
qwen3-14b
14B parameters
Base
Pull this model
Use the following command with the HoML CLI:
homl pull qwen3:14bResource Requirements
| Quantization | Disk Space | GPU Memory |
|---|---|---|
| BF16 | 28 GB | 28 GB |