nvidia
/

NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Text Generation

Model card Files Files and versions

Resources

View closed (13)

Is this model going to be seriously considered? Seeking Official Channels to Contact the Model’s Developers or an Active Community

#36 opened 1 day ago by

Inquiry about Nemotron 3 Nano technical report training details

#34 opened 8 days ago by

Failure in basic question, is it any good at programming

#31 opened 15 days ago by

Recommended parameters?

#30 opened 16 days ago by

Fix streaming output when enable_thinking is disabled

#29 opened 17 days ago by

No, Bad Logic (((

#28 opened 17 days ago by

vLLM implementation for reasoning budget

#27 opened 17 days ago by

Tool calling issue: got "True" as a String instead of a valid JSON format such as true (the primitive, unquoted value)

#25 opened 18 days ago by

use `null` instead of `Infinity` for `time_step_limit`

#20 opened 19 days ago by

Update README.md

#18 opened 20 days ago by

Recommended way of fine-tuning?

#17 opened 20 days ago by

Unexpected... "Performance"?

#15 opened 20 days ago by

doesn't do kv caching on transformers

#14 opened 20 days ago by

adaface-neurips

Does not work with dgx spark

#13 opened 21 days ago by

Actual context length

#12 opened 21 days ago by

I really hope this model works

#8 opened 22 days ago by

Simple minesweeper game is failing.

#7 opened 22 days ago by

Good model but it is very flawed in recalling input

#5 opened 23 days ago by

Problem working with long text

#4 opened 23 days ago by

Tool calling with reasoning parsing broken

#3 opened 23 days ago by