Llama 3.1 8B Instruct · 1× NVIDIA GeForce RTX 4090 · fp16
- $/hr
- $0.35
- Weights / VRAM
- 16 / 24 GB
- FP16 TFLOPS
- 165
- HF repo
meta-llama/Llama-3.1-8B-Instruct- Params
- 8.0B · llama
- Context
- 131,072
- License
- llama3.1
- Source
- model: src · gpu: knowledge
meta-llama/Llama-3.1-8B-Instruct