For some weird reason google ai studio is different from ALL quantizations
#11
by
aguspiza
- opened
Mostly never gemma3n:e4b GGUF quantizations can reply to this prompt correctly:
"calculate 4095+4095 and write the result in hexadecimal"
While the google ai studio version nails it ALWAYS, even the e2b version does it perfectly sometimes.
After testing it in ai studio several times it finally failed... so I guess ai studio is running the FP32 and it just fails less.