stepfun-ai
/

Step-3.5-Flash-Int4

Text Generation

Model card Files Files and versions

Resources

View closed (3)

Performance report with 72GB VRAM: 32 t/s

#14 opened about 18 hours ago by

Better Perplexity Alternative GGUFs

#13 opened about 22 hours ago by

chat template is broken

#12 opened 1 day ago by

Is it possible to release a version with low bit quantization?

#11 opened 3 days ago by

How do I run it using Oobabooga? I'm getting the following error

#10 opened 3 days ago by

What are the benchmarks of the 4 bit model vs the FP8 model?

#9 opened 4 days ago by

Make this model more visible on the hub

#8 opened 5 days ago by

INT8 quantization for KVCache on DGX Spark/GB10

#6 opened 5 days ago by

config.json file needed at root?

#4 opened 6 days ago by

pathosethoslogos

cool model !!

#3 opened 6 days ago by

great job！ thanks!

#1 opened 6 days ago by