Text Generation
Transformers
Safetensors
minimax_m2
neuralmagic
redhat
llmcompressor
quantized
FP4
conversational
custom_code
8-bit precision
compressed-tensors
Instructions to use RedHatAI/MiniMax-M2.5-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/MiniMax-M2.5-NVFP4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RedHatAI/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("RedHatAI/MiniMax-M2.5-NVFP4", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("RedHatAI/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 RedHatAI/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 "RedHatAI/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": "RedHatAI/MiniMax-M2.5-NVFP4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RedHatAI/MiniMax-M2.5-NVFP4
- SGLang
How to use RedHatAI/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 "RedHatAI/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": "RedHatAI/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 "RedHatAI/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": "RedHatAI/MiniMax-M2.5-NVFP4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RedHatAI/MiniMax-M2.5-NVFP4 with Docker Model Runner:
docker model run hf.co/RedHatAI/MiniMax-M2.5-NVFP4
| { | |
| "schema_version": "0.2.2", | |
| "evaluation_id": "aime25/RedHatAI/MiniMax-M2.5-NVFP4/1777382291.417811", | |
| "evaluation_timestamp": "3303957", | |
| "retrieved_timestamp": "1777382291.417811", | |
| "source_metadata": { | |
| "source_name": "lighteval", | |
| "source_type": "evaluation_run", | |
| "source_organization_name": "RedHatAI", | |
| "evaluator_relationship": "third_party" | |
| }, | |
| "eval_library": { | |
| "name": "lighteval", | |
| "version": "v0.13.0" | |
| }, | |
| "model_info": { | |
| "name": "RedHatAI/MiniMax-M2.5-NVFP4", | |
| "id": "RedHatAI/MiniMax-M2.5-NVFP4", | |
| "developer": "RedHatAI", | |
| "inference_engine": { | |
| "name": "vllm" | |
| }, | |
| "additional_details": { | |
| "provider": "hosted_vllm", | |
| "base_url": "http://0.0.0.0:8003/v1", | |
| "concurrent_requests": "8", | |
| "verbose": "False", | |
| "api_max_retry": "8", | |
| "api_retry_sleep": "1.0", | |
| "api_retry_multiplier": "2.0", | |
| "timeout": "2400.0", | |
| "num_seeds_merged": "8" | |
| } | |
| }, | |
| "evaluation_results": [ | |
| { | |
| "evaluation_name": "aime25", | |
| "source_data": { | |
| "dataset_name": "aime25", | |
| "source_type": "hf_dataset", | |
| "hf_repo": "yentinglin/aime_2025", | |
| "hf_split": "train" | |
| }, | |
| "evaluation_timestamp": "3305786", | |
| "metric_config": { | |
| "evaluation_description": "pass@k:k=1&n=1", | |
| "lower_is_better": false, | |
| "score_type": "continuous", | |
| "min_score": 0.0, | |
| "max_score": 1.0 | |
| }, | |
| "score_details": { | |
| "score": 0.7708333333333334, | |
| "details": { | |
| "seed_scores": "[0.8, 0.7, 0.8333333333333334, 0.7666666666666667, 0.8333333333333334, 0.7666666666666667, 0.6666666666666666, 0.8]", | |
| "seed_values": "[1234, 1356, 3344, 4158, 42, 5322, 5678, 9843]" | |
| }, | |
| "uncertainty": { | |
| "standard_error": { | |
| "value": 0.021304202581158678, | |
| "method": "across_seeds" | |
| }, | |
| "num_samples": 8 | |
| } | |
| }, | |
| "generation_config": { | |
| "generation_args": { | |
| "temperature": 1.0, | |
| "top_p": 0.95, | |
| "top_k": 40.0, | |
| "max_tokens": 64000, | |
| "max_attempts": 1 | |
| }, | |
| "additional_details": { | |
| "repetition_penalty": "1.0", | |
| "presence_penalty": "1.5", | |
| "seed": "1234", | |
| "min_p": "0.0" | |
| } | |
| } | |
| }, | |
| { | |
| "evaluation_name": "aime25", | |
| "source_data": { | |
| "dataset_name": "aime25", | |
| "source_type": "hf_dataset", | |
| "hf_repo": "yentinglin/aime_2025", | |
| "hf_split": "train" | |
| }, | |
| "evaluation_timestamp": "3305786", | |
| "metric_config": { | |
| "evaluation_description": "avg@n:n=1", | |
| "lower_is_better": false, | |
| "score_type": "continuous", | |
| "min_score": 0.0, | |
| "max_score": 1.0 | |
| }, | |
| "score_details": { | |
| "score": 0.7708333333333334, | |
| "details": { | |
| "seed_scores": "[0.8, 0.7, 0.8333333333333334, 0.7666666666666667, 0.8333333333333334, 0.7666666666666667, 0.6666666666666666, 0.8]", | |
| "seed_values": "[1234, 1356, 3344, 4158, 42, 5322, 5678, 9843]" | |
| }, | |
| "uncertainty": { | |
| "standard_error": { | |
| "value": 0.021304202581158678, | |
| "method": "across_seeds" | |
| }, | |
| "num_samples": 8 | |
| } | |
| }, | |
| "generation_config": { | |
| "generation_args": { | |
| "temperature": 1.0, | |
| "top_p": 0.95, | |
| "top_k": 40.0, | |
| "max_tokens": 64000, | |
| "max_attempts": 1 | |
| }, | |
| "additional_details": { | |
| "repetition_penalty": "1.0", | |
| "presence_penalty": "1.5", | |
| "seed": "1234", | |
| "min_p": "0.0" | |
| } | |
| } | |
| } | |
| ] | |
| } |