These models may *degrade* performance on prompts < 32k and only needed for LM Studio users.
3
#8 opened 1 day ago
by
ubergarm
How to run the 128k models
6
#7 opened 2 days ago
by
rogerooberg
How can I change the number of experts for inference?
1
#5 opened 12 days ago
by
win10
Seems not supporting tools calling
2
#4 opened 13 days ago
by
bingw5
Umm, another bump on the road? :/
2
#2 opened 13 days ago
by
MrDevolver
How do I extend a Qwen3 model that has been pulled by Ollama using the YaRN method?
2
#1 opened 14 days ago
by
MikeNate