Instructions to use Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, LlamaForCausalLMEagle3

tokenizer = AutoTokenizer.from_pretrained("Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4")
model = LlamaForCausalLMEagle3.from_pretrained("Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4

SGLang

How to use Inferact/MiniMax-M3-EAGLE3-GQA-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 "Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4" \
    --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": "Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4",
		"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 "Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4" \
        --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": "Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Inferact/MiniMax-M3-EAGLE3-GQA-NVFP4
```

MiniMax-M3-EAGLE3-GQA-NVFP4 / config.json

ZixiQi

Add NVFP4 W4A4 MLP-quantized EAGLE3 GQA draft (block 16, calibrated input_scale) + model card

1cc6023 verified 6 days ago

Raw

History Blame Contribute Delete

1.43 kB

	{
	"architectures": [
	"LlamaForCausalLMEagle3"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"fc_norm": true,
	"norm_output": true,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 6144,
	"initializer_range": 0.02,
	"intermediate_size": 18432,
	"max_position_embeddings": 1048576,
	"model_type": "llama",
	"num_attention_heads": 64,
	"num_hidden_layers": 1,
	"num_key_value_heads": 4,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 5000000,
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.51.0",
	"use_cache": true,
	"use_sliding_window": false,
	"vocab_size": 200064,
	"draft_vocab_size": 200064,
	"_torchspec_version": "0.1.0",
	"quantization_config": {
	"config_groups": {
	"group_0": {
	"input_activations": {
	"dynamic": false,
	"num_bits": 4,
	"type": "float",
	"group_size": 16
	},
	"weights": {
	"dynamic": false,
	"num_bits": 4,
	"type": "float",
	"group_size": 16
	},
	"targets": [
	"Linear"
	]
	}
	},
	"ignore": [
	"embed_tokens",
	"fc",
	"self_attn",
	"lm_head"
	],
	"quant_algo": "NVFP4",
	"producer": {
	"name": "modelopt",
	"version": "0.46.0.dev150+gb012e4c26"
	},
	"quant_method": "modelopt"
	}
	}