Instructions to use majentik/MiniMax-M2.7-TurboQuant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/MiniMax-M2.7-TurboQuant with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="majentik/MiniMax-M2.7-TurboQuant")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("majentik/MiniMax-M2.7-TurboQuant", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use majentik/MiniMax-M2.7-TurboQuant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "majentik/MiniMax-M2.7-TurboQuant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/MiniMax-M2.7-TurboQuant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/majentik/MiniMax-M2.7-TurboQuant

SGLang

How to use majentik/MiniMax-M2.7-TurboQuant with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "majentik/MiniMax-M2.7-TurboQuant" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/MiniMax-M2.7-TurboQuant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "majentik/MiniMax-M2.7-TurboQuant" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/MiniMax-M2.7-TurboQuant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use majentik/MiniMax-M2.7-TurboQuant with Docker Model Runner:
```
docker model run hf.co/majentik/MiniMax-M2.7-TurboQuant
```

majentik commited on May 6

Commit

a833cb4

verified ·

1 Parent(s): 077ded9

docs: Tier 2 polish — variant matrix + quant trade-off

Browse files

Files changed (1) hide show

README.md +19 -0

README.md CHANGED Viewed

@@ -141,3 +141,22 @@ If you want combined weight + KV cache compression, majentik hosts pre-quantized
 - [TurboQuant paper (arXiv 2504.19874)](https://arxiv.org/abs/2504.19874)
 - [llama-cpp-turboquant fork](https://github.com/johndpope/llama-cpp-turboquant/tree/feature/planarquant-kv-cache)
 - [Base model: MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7)

 - [TurboQuant paper (arXiv 2504.19874)](https://arxiv.org/abs/2504.19874)
 - [llama-cpp-turboquant fork](https://github.com/johndpope/llama-cpp-turboquant/tree/feature/planarquant-kv-cache)
 - [Base model: MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7)
+## Variants in this family
+(Showing 12 sibling variants under `majentik/minimax-m2.7-*`. The current variant — `TurboQuant` — is **bolded**.)
+| Variant | Runtime | Approx size | Use case |
+|---|---|---|---|
+| [RotorQuant](https://huggingface.co/majentik/minimax-m2.7-rotorquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
+| [RotorQuant-MLX-2bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-2bit) | mlx-lm | ~885 MB | Apple Silicon, smallest |
+| [RotorQuant-MLX-3bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-3bit) | mlx-lm | ~1.2 GB | Apple Silicon, small |
+| [RotorQuant-MLX-4bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-4bit) | mlx-lm | ~1.7 GB | Apple Silicon balanced |
+| [RotorQuant-MLX-5bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-5bit) | mlx-lm | ~2.1 GB | Apple Silicon, higher fidelity |
+| [RotorQuant-MLX-8bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-8bit) | mlx-lm | ~3.2 GB | Apple Silicon reference |
+| **TurboQuant** | runtime modifier | n/a | KV-cache root (weight-agnostic) |
+| [TurboQuant-MLX-2bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-2bit) | mlx-lm | ~885 MB | Apple Silicon, smallest |
+| [TurboQuant-MLX-3bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-3bit) | mlx-lm | ~1.2 GB | Apple Silicon, small |
+| [TurboQuant-MLX-4bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-4bit) | mlx-lm | ~1.7 GB | Apple Silicon balanced |
+| [TurboQuant-MLX-5bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-5bit) | mlx-lm | ~2.1 GB | Apple Silicon, higher fidelity |
+| [TurboQuant-MLX-8bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-8bit) | mlx-lm | ~3.2 GB | Apple Silicon reference |