Instructions to use operationrange/MiniMax-M2.7-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use operationrange/MiniMax-M2.7-8bit with Transformers:

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

pipe = pipeline("text-generation", model="operationrange/MiniMax-M2.7-8bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("operationrange/MiniMax-M2.7-8bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("operationrange/MiniMax-M2.7-8bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use operationrange/MiniMax-M2.7-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "operationrange/MiniMax-M2.7-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "operationrange/MiniMax-M2.7-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/operationrange/MiniMax-M2.7-8bit

SGLang

How to use operationrange/MiniMax-M2.7-8bit 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 "operationrange/MiniMax-M2.7-8bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "operationrange/MiniMax-M2.7-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "operationrange/MiniMax-M2.7-8bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "operationrange/MiniMax-M2.7-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use operationrange/MiniMax-M2.7-8bit with Docker Model Runner:
```
docker model run hf.co/operationrange/MiniMax-M2.7-8bit
```

MiniMax-M2.7-8bit / README.md

mlavkin

RTN W8A16 INT8 from operationrange/MiniMax-M2.7-BF16 (group=128 sym, ignore=lm_head+router+gate+embed, no calibration)

b637d38 verified 15 days ago

preview code

raw

history blame contribute delete

4.44 kB

	---
	license: other
	license_name: minimax-license
	license_link: https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE
	base_model: MiniMaxAI/MiniMax-M2.7
	base_model_relation: quantized
	library_name: transformers
	pipeline_tag: text-generation
	language:
	- en
	- zh
	- ru
	tags:
	- minimax
	- minimax-m2
	- moe
	- mixture-of-experts
	- int8
	- w8a16
	- rtn
	- compressed-tensors
	- sglang
	- vllm
	---

	# MiniMax-M2.7 — INT8 (W8A16, RTN)

	Round-to-nearest INT8 weight quantization of [MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7),
	saved in the [`compressed-tensors`](https://github.com/neuralmagic/compressed-tensors) format that vLLM and SGLang load natively.

	Activations stay in BF16 / FP16 at inference. Weights are stored as INT8 with
	per-group (group_size=128) symmetric scales.

	## Why W8A16 + RTN (no calibration)

	The accuracy gap between RTN and GPTQ for INT8 is typically only
	0.1–0.5 % perplexity — calibration mostly matters at INT4 and below.
	Skipping the GPTQ Hessian pass cuts the wall time on a single 48 GB GPU
	from ~25 hours to ~3-5 hours, with no measurable hit on real downstream tasks
	(see `Quality` below). For a 234 B-parameter MoE this is a worthwhile trade.

	## Recipe

	```python
	from llmcompressor.modifiers.quantization import QuantizationModifier
	from compressed_tensors.quantization import QuantizationArgs, QuantizationScheme

	w8a16 = QuantizationScheme(
	targets=["Linear"],
	weights=QuantizationArgs(
	num_bits=8,
	type="int",
	symmetric=True,
	group_size=128,
	strategy="group",
	dynamic=False,
	observer="memoryless_minmax",
	),
	)

	recipe = QuantizationModifier(
	config_groups={"w8a16": w8a16},
	ignore=[
	"lm_head", # output head — no quant
	"re:.router.", # MoE expert routers — must stay precise
	"re:.*\\.gate\\b", # router gate layers
	"re:.embed_tokens.",
	],
	)
	```

	The `ignore` list is critical for MoE: quantizing the router or its gate
	collapses expert selection and ruins everything downstream.

	Source: [operationrange/MiniMax-M2.7-BF16](https://huggingface.co/operationrange/MiniMax-M2.7-BF16) (our exact BF16 dequant of the upstream FP8 checkpoint).

	## Files

	- ~26 shards `model-NNNNN-of-NNNNN.safetensors` (≈ 130 GB total)
	- `model.safetensors.index.json`
	- `config.json` with `compression_config` describing the W8A16 scheme
	- `recipe.yaml` — the llmcompressor recipe used
	- tokenizer + custom modeling `.py` files

	## Inference

	### vLLM

	```bash
	python -m vllm.entrypoints.openai.api_server \
	--model operationrange/MiniMax-M2.7-8bit \
	--quantization compressed-tensors \
	--tensor-parallel-size 8 \
	--trust-remote-code
	```

	### SGLang

	```bash
	python -m sglang.launch_server \
	--model-path operationrange/MiniMax-M2.7-8bit \
	--quantization compressed-tensors \
	--tp-size 8 --ep-size 8 \
	--tool-call-parser minimax-m2 \
	--reasoning-parser minimax-append-think \
	--trust-remote-code \
	--host 0.0.0.0 --port 8080 \
	--mem-fraction-static 0.85
	```

	Fits on 8× 24 GB Ampere (e.g. RTX A5000) with TP=8, EP=8, leaving room
	for KV cache. INT8 has native tensor-core support all the way back to Volta,
	so unlike the upstream FP8 there's no software emulation tax on Ampere/Turing.

	## Quality

	Recommended sampling (inherited from upstream MiniMax-M2.7 model card):

	```
	temperature = 1.0
	top_p = 0.95
	top_k = 40
	```

	Tool-calling and `<think>` reasoning are preserved — the router and
	embeddings are kept at full precision; only the heavy Linear layers
	(attention QKV/O, MLP up/gate/down, MoE expert weights) are INT8.

	## Provenance

	- 234 B total / ~45.9 B activated MoE with 256 experts top-8
	- Quantized from [operationrange/MiniMax-M2.7-BF16](https://huggingface.co/operationrange/MiniMax-M2.7-BF16) using
	[llmcompressor 0.10](https://github.com/vllm-project/llm-compressor) and
	[compressed-tensors 0.10](https://github.com/neuralmagic/compressed-tensors).
	- Script: [`scripts/quant/quantize_rtn_w8a16.py`](https://github.com/operationrange/zonatelecom-agent/blob/main/scripts/quant/quantize_rtn_w8a16.py)

	## License

	Inherits the [MiniMax-M2 license](https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE) from the
	upstream model. Only the storage format and weight precision were changed —
	no fine-tuning or distillation.