Models
Resources
Pricing
Chat
Status
Log in
Sign up
Models
Llama 3
8b
mit-han-lab/Llama-3-8B-QServe
TEXT GENERATION
Concurrency Cost:
1
Model Size:
8B
Quant:
FP8
Ctx Length:
8k
License:
llama3
Architecture:
Transformer
0.0K
Cold
Loading preview...
Full Model Card (README)
Finetunes
2 models