Llama-3.1-8B-Instruct-FP8: GPU memory and hosting cost
Open weights · 8.03 billion parameters · 131,072-token context · licence llama3.1
No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.
Run it yourself
It needs 10 GB of GPU memory at fp8, the precision it ships in.
| Cloud | Cheapest instance that fits | GPUs | An hour | A month, around the clock |
|---|---|---|---|---|
| AWS | g4dn.xlarge | 1 × T4 16 GB | $0.526 | $384 |
| Azure | Standard_NC4as_T4_v3 | 1 × T4 16 GB | $0.526 | $384 |
| Google Cloud | g2-standard-4 | 1 × L4 24 GB | $0.7068 | $516 |
| Alibaba Cloud | ecs.gn6i-c4g1.xlarge | 1 × T4 16 GB | $1.12 | $816 |
More from NVIDIA
- Qwen3.6-35B-A3B-NVFP4
- NVIDIA-Nemotron-3-Nano-4B-BF16
- Gemma-4-31B-IT-NVFP4
- Qwen2.5-VL-7B-Instruct-NVFP4
- NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- Qwen3.5-122B-A10B-NVFP4
Similar size, open weights
List prices collected 5 October 2026, refreshed every three hours. No negotiated rates or taxes.