Llama 3.3 70B Instruct · 4× NVIDIA GeForce RTX 4090 · fp8
- $/hr
- $1.40
- Weights / VRAM
- 71 / 96 GB
- FP16 TFLOPS
- 660
- HF repo
meta-llama/Llama-3.3-70B-Instruct- Params
- 70.6B · llama
- Context
- 131,072
- License
- llama3.3
- Source
- model: src · gpu: knowledge
meta-llama/Llama-3.3-70B-Instruct