---
library_name: mlx
tags:
  - mlx
  - quantized
  - mixed-precision
  - minimax
  - minimax_m2
  - moe
license: other
license_name: minimax-m2-license
license_link: LICENSE
base_model: MiniMaxAI/MiniMax-M2.7
base_model_relation: quantized
pipeline_tag: text-generation
language: en
---

# MiniMax-M2.7 — 203 GB (MLX)

Earlier build of the MiniMax-M2.7 mixed-precision MLX family, by [baa.ai](https://baa.ai).

## Current builds

For updated builds with HumanEval results and recommended inference settings, see:

| Variant | Size | Link |
|---|---|---|
| 100 GB | 100.1 GB | [baa-ai/MiniMax-M2.7-RAM-100GB-MLX](https://huggingface.co/baa-ai/MiniMax-M2.7-RAM-100GB-MLX) |
| 111 GB | 110.9 GB | [baa-ai/MiniMax-M2.7-RAM-111GB-MLX](https://huggingface.co/baa-ai/MiniMax-M2.7-RAM-111GB-MLX) |
| 116 GB | 116.0 GB | [baa-ai/MiniMax-M2.7-RAM-116GB-MLX](https://huggingface.co/baa-ai/MiniMax-M2.7-RAM-116GB-MLX) |
| 120 GB | 120.1 GB | [baa-ai/MiniMax-M2.7-RAM-120GB-MLX](https://huggingface.co/baa-ai/MiniMax-M2.7-RAM-120GB-MLX) |

## Usage

```python
from mlx_lm import load, generate

model, tokenizer = load("baa-ai/MiniMax-M2.7-RAM-203GB-MLX")
response = generate(model, tokenizer, prompt="Hello!", max_tokens=512)
print(response)
```

## License

Inherited from the upstream [MiniMax-M2.7 license](https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE): non-commercial use permitted; commercial use requires written authorization from MiniMax.

---
*Quantized by [baa.ai](https://baa.ai)*