✅ — Google Cloud A3 (8x H100) Can Run Qwen 2.5 72B
The Google Cloud A3 (8x H100) packs 640GB VRAM. Qwen 2.5 72B needs ~39.6GB. You're good to go.
✅ Plenty of headroom
Hardware Specs
- GPU
- Google Cloud A3 (8x H100)
- VRAM
- 640 GB
- Bandwidth
- 26400 GB/s
- MSRP
- $0
Model Requirements
- Model
- Qwen 2.5 72B
- Parameters
- 72B
- VRAM (Q4)
- ~39.6 GB
- Context
- N/A
Estimated Performance
550 tok/s
Estimated inference speed (Q4 quantization)