QriticalBeta
Open Model Catalogue
Meta
Meta
Text generation

Llama 3.3 70B

meta-llama/Llama-3.3-70B-Instruct

Meta flagship — multi-GPU

Deploy Llama 3.3 70B nowView on HuggingFace
Parameters
70B
Min VRAM
≈ 160 GB
Hardware
2 × 80 GB GPU
This model requires accepting its licence on HuggingFace and a HuggingFace token in your account credentials.
OpenAI-compatible API with a per-workload key — drop-in for existing SDKs.
Dedicated GPUs — your model, your instance, no shared queues.
Billed by the second with auto-shutdown — never pay for idle time you didn't plan.