Language
MiniMax M3 (MoE, native multimodal)
MiniMax M3 — ~428B total / ~23B active MoE with native multimodal training. MiniMax Sparse Attention (MSA) delivers 9× prefill and 15× decode speedups vs M2 at 1M context. Note: GGUF builds currently fall back to dense attention; sparse attention not yet supported in llama.cpp.
MITSource verified
Specification
Model ID
minimax-m3Family
minimax
Modality
Language
Parameters
428B (MoE, 23B active)
Context
1,048,576 tokens
Quantization
Q4_K_M
Weights
214.2 GB
Minimum RAM
192 GB
Source
Weights and provenance.
Repository
Registry license
MIT
Access
Open — weights fetch without accepting additional terms.
The licence above is the registry's. The source repository either states nothing, states the catch-all “other”, or carries a licence link and base model that its own tag contradicts — a re-quantisation inherits the terms of the weights it derives from. The registry's licence is the one to rely on.
Serve it
# Pull the weights onto a node
tenzro model download minimax-m3
# Serve it
tenzro model serve minimax-m3
# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
-X POST -H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,
"method":"tenzro_getModel",
"params":[{"model_id":"minimax-m3"}]}'Same family