Span Spek
spanspek
AI & ML interests
None yet
Recent Activity
new activity 2 days ago
nvidia/Nemotron-Cascade-2-30B-A3B:There's got to be a better way. new activity 3 days ago
nvidia/Nemotron-Cascade-2-30B-A3B:Tool calling ability liked a model 3 days ago
nvidia/Nemotron-Cascade-2-30B-A3BOrganizations
None yet
There's got to be a better way.
15
#6 opened 2 days ago
by
phil111
Tool calling ability
๐ฅ 1
1
#3 opened 3 days ago
by
spanspek
Request: Casade post-train Nemotron-3-Super
๐ฅ 1
1
#21 opened 5 days ago
by
spanspek
Error on LMStudio.
5
#1 opened 10 days ago
by
ntp777
What impact has quantization had on model performance / ability?
1
#4 opened 19 days ago
by
spanspek
Actual use cases for this model
3
#8 opened 24 days ago
by
spanspek
Model performance
2
#1 opened 24 days ago
by
spanspek
Excellent model
#3 opened 29 days ago
by
spanspek
Insane performance
โค๏ธ 9
3
#4 opened about 1 month ago
by
AntDX316
Information about the dataset is needed
๐ 1
2
#1 opened about 2 months ago
by
Blizado
FP-8 version please ๐ฅบ
3
#7 opened about 2 months ago
by
nikhilfande
What quantization is the base model?
2
#8 opened about 2 months ago
by
spanspek
Extremely misleading benchmarks
โ 1
5
#1 opened 3 months ago
by
rombodawg
Phenomenal model
3
#1 opened about 2 months ago
by
spanspek
Deepseek architecture?
7
#1 opened 2 months ago
by
spanspek
Feedback from testing
๐ 1
1
#1 opened 2 months ago
by
spanspek
Feedback from running in LM Studio 0.39.3 with v1.103.2 of llama.cpp
29
#1 opened 2 months ago
by
spanspek
Possible use-cases?
#1 opened 2 months ago
by
spanspek
A few observations - Memory estimation & thinking is getting stuck in loops
#1 opened 2 months ago
by
spanspek