MiniMax M3
A native multimodal model with sparse attention for million-token contexts.
- Published size
- ~428B
- Active parameters
- 23B
- Context window
- 1M
- Architecture
- MoE · vision
- License
- MiniMax Community
Deployment considerations
Measure long-context prefill and decode separately, and verify support for the model's sparse-attention implementation.
The publisher describes approximately 428B total and 23B activated parameters, with text, image, and video inputs.
GPU memory estimates and minimum / recommended configurations are pending. This profile does not contain measured deployment results.
GPU requirements
- Minimum
- —GPU / VRAM · pending
- Recommended
- —GPU / VRAM · pending
Memory estimates and tested configurations will appear here after checkpoint review and deployment testing.
No invented leaderboards.
Latency, throughput, and cost per token will appear here after a reproducible run. Until then, this page helps you understand the model—not predict its performance.
MiniMax M3 deployment FAQ
How much GPU memory does MiniMax M3 need?
The full checkpoint weight footprint is pending review. Minimum and recommended GPU configurations will be added after testing; the model name or active parameter count alone is not a memory requirement.
Has BenchGrid benchmarked MiniMax M3?
Not yet. This profile contains publisher specifications and calculated weight-memory estimates. We do not currently publish measured latency, throughput, or cost per token for this model.
Where do these specifications come from?
The specifications are based on the official MiniMax model card linked on this page. Memory estimates use the stated total parameter count, including inactive experts for MoE models. Nominal model sizes are labeled with ~.
Explore your compute options.
Check available hardware, quotas, and current pricing with the provider. These links are not verified deployments or performance recommendations.
