vito95311/Qwen3-Omni-30B-A3B-Thinking-GGUF-INT8FP16 · Discussions

Resources

View closed (1)

Path hardcoded in .modelfile

#7 opened about 2 months ago by

How much vram?

#6 opened about 2 months ago by

Support for tools / function calling?

#4 opened about 2 months ago by

Error while loading model

#3 opened about 2 months ago by

有其他量化版本嗎?

#2 opened about 2 months ago by

why the int8 and fp16 model size both are 31GB?

#1 opened about 2 months ago by