Models
Resources
Pricing
Chat
Status
Log in
Sign up
Models
Llama 3
70b
predibase/Meta-Llama-3-70B-dequantized
TEXT GENERATION
Concurrency Cost:
4
Model Size:
70B
Quant:
FP8
Ctx Length:
8k
Tool Calling:
Supported
Architecture:
Transformer
Cold
Loading preview...
Full Model Card (README)