Instructions to use inference-optimization/MiniMax-M2.5-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inference-optimization/MiniMax-M2.5-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="inference-optimization/MiniMax-M2.5-NVFP4", 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("inference-optimization/MiniMax-M2.5-NVFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("inference-optimization/MiniMax-M2.5-NVFP4", 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 inference-optimization/MiniMax-M2.5-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inference-optimization/MiniMax-M2.5-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inference-optimization/MiniMax-M2.5-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inference-optimization/MiniMax-M2.5-NVFP4

SGLang

How to use inference-optimization/MiniMax-M2.5-NVFP4 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 "inference-optimization/MiniMax-M2.5-NVFP4" \
    --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": "inference-optimization/MiniMax-M2.5-NVFP4",
		"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 "inference-optimization/MiniMax-M2.5-NVFP4" \
        --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": "inference-optimization/MiniMax-M2.5-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inference-optimization/MiniMax-M2.5-NVFP4 with Docker Model Runner:
```
docker model run hf.co/inference-optimization/MiniMax-M2.5-NVFP4
```

MiniMax-M2.5-NVFP4

Model Overview

Model Architecture: MiniMaxM2ForCausalLM
- Input: Text
- Output: Text
Model Optimizations:
- Weight quantization: FP4
Intended Use Cases:
- Reasoning.
- Function calling.
- Subject matter experts via fine-tuning.
- Multilingual instruction following.
- Translation.
Out-of-scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws).
Release Date: 02/12/2026
Version: 1.0
Model Developers: RedHat (Neural Magic)

Model Optimizations

This model was obtained by quantizing the weights and activations of MiniMax-M2.5 to FP4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. Only the weights and activations of the linear operators within transformers blocks of the language model are quantized.

Deployment

This model can be deployed efficiently using the vLLM backend, as shown in the example below.

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/MiniMax-M2.5-NVFP4"
number_gpus = 1
sampling_params = SamplingParams(temperature=1.0, top_p=0.95, top_k=40, min_p=0, max_tokens=256)

messages = [
    {"role": "user", "content": prompt}
]

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]

prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, tensor_parallel_size=number_gpus)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)

vLLM aslo supports OpenAI-compatible serving. See the documentation for more details.

Creation

Creation details

This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below.

import torch
from datasets import load_dataset
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer

from llmcompressor import oneshot
from llmcompressor.modeling.minimax_m2 import (  # noqa: F401
    CalibrationMiniMaxM2SparseMoeBlock,
)
from llmcompressor.modifiers.quantization import QuantizationModifier

# Load the model
model_id = "inference-optimization/MiniMax-M2.5-BF16"
config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, dtype=torch.bfloat16, config=config,trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
# MoE calibration is handled automatically by the pipeline.
# The `CalibrationMiniMaxM2SparseMoeBlock` modules (from
# `llmcompressor.modeling.minimax_m2`) will be applied during calibration to enable
# proper expert calibration. These replace the original
# `MiniMaxM2SparseMoeBlock` class from
# `transformers.models.minimax_m2.modeling_minimax_m2`.

# Select calibration dataset.
DATASET_ID = "HuggingFaceH4/ultrachat_200k"
DATASET_SPLIT = "train_sft"

# Select number of samples. 512 samples is a good place to start.
# Increasing the number of samples can improve accuracy.
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=f"{DATASET_SPLIT}[:{NUM_CALIBRATION_SAMPLES}]")
ds = ds.shuffle(seed=42)


def preprocess(example):
    return {
        "text": tokenizer.apply_chat_template(
            example["messages"],
            tokenize=False,
        )
    }


ds = ds.map(preprocess)


# Tokenize inputs.
def tokenize(sample):
    return tokenizer(
        sample["text"],
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
        add_special_tokens=False,
    )


ds = ds.map(tokenize, remove_columns=ds.column_names)

moe_ignores = [
    "lm_head",
    "re:.*block_sparse_moe.gate$",
]

# Experts live under `model.layers.*.block_sparse_moe.experts.<idx>.(w1|w2|w3)`.
EXPERT_TARGET_REGEX = [
    "re:.*block_sparse_moe\\.experts\\.\\d+\\.w1$",
    "re:.*block_sparse_moe\\.experts\\.\\d+\\.w2$",
    "re:.*block_sparse_moe\\.experts\\.\\d+\\.w3$",
]

recipe = QuantizationModifier(
    targets=EXPERT_TARGET_REGEX,
    scheme="NVFP4",
    weight_observer="mse",
    ignore= moe_ignores
)


# Apply algorithms.
oneshot(
    model=model,
    dataset=ds,
    processor=tokenizer,
    recipe=recipe,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    sequential_targets=["MiniMaxM2DecoderLayer"],
)

# Save to disk compressed.
SAVE_DIR = model_id.rstrip("/").split("/")[-1] + "-NVFP4"
model.save_pretrained(SAVE_DIR, save_compressed=True)
tokenizer.save_pretrained(SAVE_DIR)

</details>
 



## Evaluation

The model was evaluated on the ifeval, mmlu_pro and gsm8k_platinum  using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), on reasoning tasks using [lighteval](https://github.com/neuralmagic/lighteval/tree/reasoning).
[vLLM](https://docs.vllm.ai/en/stable/) was used for all evaluations.


<details>
  <summary>Evaluation details</summary>

  Deploy using vllm to create an OpenAI-compatible API endpoint:

- vLLM:
    ```shell
    vllm serve RedHatAI/MiniMax-M2.5-NVFP4 --max-model-len 262144 --reasoning-parser deepseek_r1
    ```

  **lm-evaluation-harness**

lm_eval --model local-chat-completions
--tasks mmlu_pro_chat
--model_args "model=RedHatAI/MiniMax-M2.5-NVFP4,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200"
--num_fewshot 0
--apply_chat_template
--gen_kwargs "do_sample=True,temperature=1.0,top_p=0.95,top_k=40,min_p=0.0,max_gen_toks=64000

lm_eval --model local-chat-completions
--tasks ifeval
--model_args "model=RedHatAI/MiniMax-M2.5-NVFP4,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200"
--num_fewshot 0
--apply_chat_template
--gen_kwargs "do_sample=True,temperature=1.0,top_p=0.95,top_k=40,min_p=0.0,max_gen_toks=64000

lm_eval --model local-chat-completions
--tasks gsm8k_platinum_cot_llama
--model_args "model=RedHatAI/MiniMax-M2.5-NVFP4,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200"
--num_fewshot 0
--apply_chat_template
--gen_kwargs "do_sample=True,temperature=1.0,top_p=0.95,top_k=40,min_p=0.0,max_gen_toks=64000


**lighteval**

lighteval_model_arguments.yaml
```yaml 
model_parameters:
  model_name: RedHatAI/MiniMax-M2.5-NVFP4
  dtype: auto
  gpu_memory_utilization: 0.9
  max_model_length: 40960
  generation_parameters:
    temperature: 1.0
    top_k: 40
    min_p: 0.0
    top_p: 0.95
    max_new_tokens: 64000

lighteval endpoint litellm lighteval_model_arguments.yaml  \
  "aime25|0,math_500|0,gpqa:diamond|0"

Accuracy

Benchmark	inference-optimization/MiniMax-M2.5-BF16	inference-optimization/MiniMax-M2.5-NVFP4	Recovery (%)
GSM8k Platinum (0-shot)	95.15	93.91	98.70
IfEval (0-shot)	92.05	89.89	97.66
AIME 2025	87.50	77.08	88.10
GPQA diamond	83.67	80.30	95.98
Math 500	87.33	87.73	100.46
MMLU Pro Chat	80.83	80.08	99.07

Downloads last month: 316

Safetensors

Model size

130B params

Tensor type

F32

BF16

F8_E4M3

Model tree for inference-optimization/MiniMax-M2.5-NVFP4

Base model

MiniMaxAI/MiniMax-M2.5

Quantized

(67)

this model