✅ — B200 Can Run Llama 3.1 8B
The B200 packs 192GB VRAM. Llama 3.1 8B needs ~4.4GB. You're good to go.
✅ Plenty of headroom
Hardware Specs
- GPU
- B200
- VRAM
- 192 GB
- Bandwidth
- 3350 GB/s
- MSRP
- $0
Model Requirements
- Model
- Llama 3.1 8B
- Parameters
- 8B
- VRAM (Q4)
- ~4.4 GB
- Context
- N/A
Estimated Performance
628 tok/s
Estimated inference speed (Q4 quantization)