unsloth

/

Qwen3-VL-235B-A22B-Thinking-1M-GGUF

like 1

Follow

Unsloth AI 12k

Am I missing something or why are the GGUF sizes different for same quants between this repo and the "non-1M" version??

The "non-1M" unsloth/Qwen3-VL-235B-A22B-Thinking-GGUF repo lists these:

while the 1M version lists much smaller sizes (ie 8-bit quants)???

Update!

It's of course because there are some files missing...

@DanielLiang