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
Source license
other
Access
Open — weights fetch without accepting additional terms.
The registry records this model as MIT while the source repository states other. Both are shown here rather than one being preferred. Treat the stricter of the two as binding until the discrepancy is resolved upstream.
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