Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
MiniMax-M3-GGUF-MoQ – AI Model by kaitchup | AlphaNeural AI
You can deploy this model and start earning money today!
kaitchup
/
MiniMax-M3-GGUF-MoQ
like
0
gguf
MiniMaxAI/MiniMax-M3
quantized
other
endpoints_compatible
us
imatrix
conversational
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
The Kaitchup -- AI on a Budget
Subscribe and Support
GGUF models made with the method ("Mixture of Quantizations") proposed by
Waleed Ahmad
. I also used Unsloth
M3's imatrix
for calibration.
More details and evaluation here:
MiniMax M3 GGUF Quantization: From 852 GB to ~150 GB Without Breaking Accuracy
image
Avoid using the MoQ-2.5.
Compute Sponsorship:
Verda
. I used 2 B300s for quantization and evaluation.