Models
Resources
Pricing
Chat
Status
Log in
Sign up
Models
Qwen 3
32b
iotaminer/affine-5FPA7Ne4qJbY9N6xCbG9Thm5A8KopBZQdVja4TY2bz9N6pes
TEXT GENERATION
Concurrency Cost:
2
Model Size:
32B
Quant:
FP8
Ctx Length:
32k
Published:
Apr 1, 2026
Architecture:
Transformer
Cold
Loading preview...
Full Model Card (README)