✅ — NVIDIA GB200 NVL72 Can Run Qwen 2.5 32B
The NVIDIA GB200 NVL72 packs 14131.2GB VRAM. Qwen 2.5 32B needs ~17.6GB. You're good to go.
✅ Plenty of headroom
Hardware Specs
- GPU
- NVIDIA GB200 NVL72
- VRAM
- 14131.2 GB
- Bandwidth
- 576000 GB/s
- MSRP
- $3,000,000
Model Requirements
- Model
- Qwen 2.5 32B
- Parameters
- 32B
- VRAM (Q4)
- ~17.6 GB
- Context
- N/A
Estimated Performance
27000 tok/s
Estimated inference speed (Q4 quantization)
Buy vs Rent — Do the Math
Rent breaks even after 10,344,827hrs • Used pays off faster