mudler
/

Qwen3.5-35B-A3B-APEX-GGUF

Text Generation

Mixture of Experts

mixed-precision

Model card Files Files and versions

Resources

View closed (0)

Getting "///////" output with this and other quants

#8 opened 6 days ago by

When NVFP4 will arrive completely to llama.cpp and used together with APEX method - this model will become nearly perfect !

#7 opened 7 days ago by

Precision discrepancy between variants

#6 opened 9 days ago by

Great work

#5 opened 9 days ago by

MLX versions

#4 opened 12 days ago by

Qwopus/Opus distillation possible?

#3 opened 15 days ago by

Broken ollama links

#2 opened 15 days ago by

Is I-* variant models supposed to be better or worse than non I-* variant?

#1 opened 15 days ago by