The sampling acceleration from nvfp4 quantization in Krea2 is not significant.
6
#6 opened 1 day ago
by 
Aca233
Workflow LoRAs missing?
5
#5 opened 1 day ago
by 
peoplesbayonet
text encoder gguf version quant 4 qwen 3 vl ?
1
#4 opened 1 day ago
by 
Ryu-Sena
How is LoRa krea2_turbo_lora_rank_64_bf16.safetensors supposed to work, what's it good for?
1
#3 opened 2 days ago
by 
FlensMan
qwen3vl_4b_nvfp4?
👍 3
2
#1 opened 3 days ago
by 
shivshankar