✅ — H100 NVL Can Run Llama 3.1 70B
The H100 NVL packs 188GB VRAM. Llama 3.1 70B needs ~38.5GB. You're good to go.
✅ Plenty of headroom
Hardware Specs
- GPU
- H100 NVL
- VRAM
- 188 GB
- Bandwidth
- 3350 GB/s
- MSRP
- $0
Model Requirements
- Model
- Llama 3.1 70B
- Parameters
- 70B
- VRAM (Q4)
- ~38.5 GB
- Context
- N/A
Estimated Performance
72 tok/s
Estimated inference speed (Q4 quantization)