QriticalBeta
Open Model Catalogue
Meta
Meta
Text generation

Llama 3.1 8B

meta-llama/Llama-3.1-8B-Instruct

Meta flagship small instruct

Deploy Llama 3.1 8B nowView on HuggingFace
Parameters
8B
Min VRAM
≈ 20 GB
Hardware
1 × 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.