llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35'
#13 opened about 21 hours ago
by
HazMatt69
How different is this model from Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF
1
#12 opened 1 day ago
by
j5IGNPff2vG
[Help] Why is Qwopus3.5-27B-v3 outputting its internal thinking and duplicating text?
π 1
2
#11 opened 5 days ago
by
hestman
Failed to generate a valid tool call.
9
#10 opened 6 days ago
by
lktinhtemp
Can you turn off CoT with native enable_reasoning?
#9 opened 9 days ago
by
barmyman
Doesnt work in lm studio
3
#8 opened 9 days ago
by
scottyboy552
CUDOS very good model
2
#7 opened 9 days ago
by
Ukro
Vision removed in this one ?
β 4
9
#5 opened 10 days ago
by
siraxe
[Request] Is it possible to provide Qwopus3.5-35B-A3B-v3?
ππ₯ 16
#4 opened 10 days ago
by
KeenZZZ
K_XL / K_P Quantization?
#3 opened 10 days ago
by
etorre
Fine tune uncensored version instead?
π 6
3
#2 opened 10 days ago
by
zxcepsycho