MiniMax-M2.7
Support summary
MiniMax-M2.7 is a checkpoint published by MiniMax, built on the MiniMaxM2ForCausalLM architecture. Official recipes or cookbooks cover vLLM and SGLang, without pinning a stable release. TensorRT-LLM lists its architecture, but not this exact checkpoint.
- Documented hardware
- NVIDIA / CUDA and AMD / ROCm
- Documented quantization
- FP8
- Documented features
- Reasoning parsers, Tensor parallelism, and Tool calling
- Configured context
- 204,800 tokens
- License
- other
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- MiniMax
- Task
- text generation
- License
- other
- Library
- transformers
- Architecture
- MiniMaxM2ForCausalLM
- Weight tensor elements
- 228.7B
- Tensor types
- F32, BF16, F8_E4M3
- Quantization
- fp8
- Configured context
- 204,800 tokens
- Weight access
- Public
- Repository created
- 2026-04-09
Model notes and sources
- MiniMaxAI/MiniMax-M2.7 · publisher model card
- MiniMaxAI/MiniMax-M2.7 · Hugging Face metadata
- MiniMaxAI/MiniMax-M2.7 · publisher configuration
- vllm · models/MiniMaxAI/MiniMax-M2.7.yaml
- sglang · docs/src/snippets/autoregressive/minimax-m27-deployment.jsx
- sglang · docs/cookbook/autoregressive/MiniMax/MiniMax-M2.7.mdx
- vllm · MiniMax/MiniMax-M2.md
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/MiniMaxAI/MiniMax-M2.7.yamlReviewed | No supported release indexed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | Version not pinnedRecipe / cookbook | Documented recipeSource 1: sglang · docs/cookbook/autoregressive/MiniMax/MiniMax-M2.7.mdxSource 2: sglang · docs/src/snippets/autoregressive/minimax-m27-deployment.jsxReviewed | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||