MiniMax-M2.7
Official · FP8 · safetensors
Runtime certified: Transformers vLLM SGLang
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| FP8 | safetensors | 8 | Official | Runtime certified |
MiniMax · General · MiniMax M2.7
MiniMax M2.7: Specs, GPU Requirements and License
MiniMax M2.7 is a recent General release in the MiniMax family, certified from its immutable official source revision.
Separate Commercial License Required
Compare this model
Total parameters229.0B
Active parameters24.0B
Context window204,800 tokens
Release statusRecent · Recent
ArchitectureMiniMaxM2ForCausalLM
ModalitiesText
LicenseMiniMax M2.7 Non-Commercial License
Deployment stateDeployable with certified configuration
Commercial stateSeparate Commercial License Required
Release date2026-04-09
Architecture, strengths and use cases
MiniMax M2.7 is an official self-hostable MiniMax release in the MiniMax General track. It uses MiniMaxM2ForCausalLM, carries 229B / 24B MoE, supports a verified context window of 204,800 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
MiniMax M2.7 uses MiniMaxM2ForCausalLM with 229B / 24B MoE. The stored architecture profile records 62 layers, hidden width 3072, 48 attention heads and a 204,800 token context ceiling where the official configuration publishes those fields.
Verified MiniMaxM2ForCausalLM architecture
204,800 token certified context
Official FP8, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed transformers, vllm, sglang runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Separate Commercial License Required
A separate commercial license or authorization is required. No commercial hosting offer is shown.
License and self-hosting considerations
The full 229B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
MiniMax M2.7 is published under MiniMax M2.7 Non-Commercial License. The release-scoped official license link and verification date are retained with the catalogue record.
Separate Commercial License Required. A separate commercial license or authorization is required. No commercial hosting offer is shown.
Alternatives and sibling variants
MiniMax M3, MiniMax M2.5, MiniMax M2.1
Release timeline
minimax/minimax/minimax-m2-7
Source details
Source revision: c138b20640417457b4614efc2bd484f84839f87024c40db6defde246235ebe0b
Frequently asked questions
How much VRAM does MiniMax M2.7 require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support MiniMax M2.7?
Certified upstream runtime evidence is available for transformers, vllm, sglang.
Can MiniMax M2.7 be used commercially?
The stored commercial classification is Separate Commercial License Required. Consult the official MiniMax M2.7 Non-Commercial License terms for the final obligations.
Official references
Last verified: 2026-08-26