What Are the Space Requirements for Large Language Model (LLM)?

Unable to discover how much disk space is needed for the new LLM models like Qwen and DeepSeek models.

The disk space needed for LLM models like Qwen and DeepSeek depends on the model size and precision. Here’s a quick overview:

Qwen Models:

• Qwen-7B: ~16.1 GB (FP16)
• Qwen-14B: ~32.2 GB (FP16)
• Qwen-72B: ~165.6 GB (FP16)

DeepSeek Models:

• DeepSeek-R1 (Full Model): ~1,342 GB (FP16)
• Distilled versions (e.g., DeepSeek-R1-Distill-Qwen-7B): ~16 GB

Storage also can be reduced by performing Model Optimization -NNCF.