Skip to content

MiniMax-M1

Released 2025-06 · reasoning · 1.0M tokens · 0 benchmarks · Open weight

Editorial notes

Primer modelo open-weight de razonamiento con hybrid attention. 456B total / 45.9B activos. Comparable a DeepSeek-R1.

Spec sheet

Company
MiniMax
Country
CN
Type
reasoning
Release
2025-06
Context
1.0M tokens
Params total
456B
Params active (MoE)
45.9B
License
apache-2.0
Quants
BF16, Q8_0, Q5_K_M, Q4_K_M
Slug
minimax-m1
No scores published for this model. The editorial notes have additional context.
Cite this model
BibTeX · APA

BibTeX

@misc{frontier-minimax-m1,
  title  = {MiniMax-M1},
  author = {{MiniMax}},
  year   = {2025},
  note   = {Frontier Benchmarks AI atlas. Accessed 2026-05-08},
  url    = {https://frontierbenchmarks.com/models/minimax-m1}
}

APA

MiniMax (2025). MiniMax-M1 [Large language model]. Frontier Benchmarks AI. Retrieved 2026-05-08, from https://frontierbenchmarks.com/models/minimax-m1

Citation reflects the atlas page, not the original model paper. For the paper, see the "Resources" section above.