Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
MiniMaxAI
/
MiniMax-M2
like
1.46k
Follow
MiniMax
3.65k
Text Generation
Transformers
Safetensors
minimax_m2
conversational
custom_code
Eval Results
fp8
arxiv:
2504.07164
arxiv:
2509.06501
arxiv:
2509.13160
License:
modified-mit
Model card
Files
Files and versions
xet
Community
54
Deploy
Use this model
mtp or other speculative decoding method?
#34
by
CHNtentes
- opened
Nov 5, 2025
Discussion
CHNtentes
Nov 5, 2025
glm 4.5 can decode 2~3x faster with mtp enabled
See translation
Edit
Preview
Upload images, audio, and videos by dragging in the text input, pasting, or
clicking here
.
Tap or paste here to upload images
Comment
·
Sign up
or
log in
to comment
