Models
Resources
Pricing
Chat
Status
Log in
Sign up
Models
Qwen 3
1b7
JameSand/qwen3-1.7b-base-svd-muon-adam-lr3e-6-minV-bs128-kl0.0-stampede3-global_step_200
TEXT GENERATION
Concurrency Cost:
1
Model Size:
2B
Quant:
BF16
Ctx Length:
32k
Published:
Apr 15, 2026
Architecture:
Transformer
Cold
Loading preview...
Full Model Card (README)
Finetunes
1 models