Instructions to use amd/MiniMax-M3-MXFP4-AttnFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/MiniMax-M3-MXFP4-AttnFP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="amd/MiniMax-M3-MXFP4-AttnFP8", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("amd/MiniMax-M3-MXFP4-AttnFP8", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("amd/MiniMax-M3-MXFP4-AttnFP8", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amd/MiniMax-M3-MXFP4-AttnFP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/MiniMax-M3-MXFP4-AttnFP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/MiniMax-M3-MXFP4-AttnFP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/amd/MiniMax-M3-MXFP4-AttnFP8

SGLang

How to use amd/MiniMax-M3-MXFP4-AttnFP8 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 "amd/MiniMax-M3-MXFP4-AttnFP8" \
    --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": "amd/MiniMax-M3-MXFP4-AttnFP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "amd/MiniMax-M3-MXFP4-AttnFP8" \
        --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": "amd/MiniMax-M3-MXFP4-AttnFP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use amd/MiniMax-M3-MXFP4-AttnFP8 with Docker Model Runner:
```
docker model run hf.co/amd/MiniMax-M3-MXFP4-AttnFP8
```

Model Overview

Model Architecture: MiniMaxM3SparseForConditionalGeneration
- Input: Text, Image
- Output: Text
Supported Hardware Microarchitecture: AMD MI350/MI355
ROCm: 7.1.1
PyTorch: 2.10.0
Transformers: 5.2.0
Operating System(s): Linux
Inference Engine: vLLM
Model Optimizer: AMD-Quark
- Weight quantization: OCP MXFP4, Static; self_attn Perchannel, FP8E4M3, Static
- Activation quantization: OCP MXFP4, Dynamic; self_attn Pertoken, FP8E4M3, Dynamic

Model Quantization

The model was quantized from MiniMaxAI/MiniMax-M3 using AMD-Quark. The weights are quantized to MXFP4 and activations are quantized to MXFP4, and self_attn layers are quantized to PTPC-FP8.

Quantization scripts:

from quark.torch import LLMTemplate, ModelQuantizer

# --- Register template ---
minimax_m3_vl_template = LLMTemplate(
    model_type="minimax_m3_vl",
    kv_layers_name=["*language_model.*k_proj", "*language_model.*v_proj"],
    q_layer_name="*language_model.*q_proj",
    exclude_layers_name=[
        "*lm_head",
        "*vision_tower*",
        "*multi_modal_projector*",
        "*patch_merge_mlp*",
        "*block_sparse_moe.gate",
    ],
)
LLMTemplate.register_template(minimax_m3_vl_template)
print(f"[INFO]: Registered template '{minimax_m3_vl_template.model_type}'")

# --- Configuration ---
model_dir = "MiniMaxAI/MiniMax-M3"
output_dir = "amd/MiniMax-M3-MXFP4-AttnFP8"
quant_scheme = "mxfp4"
# Per-layer override: self_attn (q/k/v/o_proj) -> ptpc_fp8 instead of mxfp4.
# Equivalent to:  --layer_quant_scheme '*self_attn*' ptpc_fp8
layer_config = {
    "*self_attn*": "ptpc_fp8",
}
exclude_layers = [
    "*lm_head",
    "*vision_tower*",
    "*multi_modal_projector*",
    "*patch_merge_mlp*",
    "*block_sparse_moe.gate",
    "*mlp.gate_proj",
    "*mlp.up_proj",
    "*mlp.down_proj",
]

# --- Build quant config from template ---
template = LLMTemplate.get("minimax_m3_vl")
quant_config = template.get_config(
    scheme=quant_scheme,
    layer_config=layer_config,
    exclude_layers=exclude_layers,
)

# --- File-to-file quantization (memory-efficient, no full model loading) ---
quantizer = ModelQuantizer(quant_config)
quantizer.direct_quantize_checkpoint(
    pretrained_model_path=model_dir,
    save_path=output_dir,
)
print(f"[INFO]: Quantization complete. Output saved to {output_dir}")

Evaluation

The model was evaluated on gsm8k benchmarks using the vllm framework.

Accuracy

Benchmark	MiniMaxAI/MiniMax-M3	amd/MiniMax-M3-MXFP4-AttnFP8(this model)	Recovery
gsm8k (flexible-extract)	95.30	94.01	98.65%

Reproduction

The GSM8K results were obtained using the lm-eval framework, based on the Docker image rocm/pytorch-private:vllm-hy-mm-06112026. The vLLM shipped in that image was used as-is, with the patch from this PR (#45794) applied on top.

Launching server

vllm serve /mnt/amd/MiniMax-M3-MXFP4-AttnFP8 \
  --trust-remote-code \
  --block-size 128 \
  --tensor-parallel-size 8 \
  --attention-backend TRITON_ATTN \
  --mm-encoder-tp-mode data \
  --mm-encoder-attn-backend ROCM_AITER_FA \
  --tool-call-parser minimax_m3 \
  --enable-auto-tool-choice \
  --reasoning-parser minimax_m3 \
  --moe-backend emulation

Evaluating model in a new terminal

lm_eval \
  --model local-chat-completions \
  --model_args "model=/mnt/amd/MiniMax-M3-MXFP4-AttnFP8,base_url=http://127.0.0.1:8000/v1/chat/completions,num_concurrent=32,max_gen_toks=16384" \
  --tasks gsm8k \
  --num_fewshot 5 \
  --batch_size 1 \
  --apply_chat_template \
  --fewshot_as_multiturn

Downloads last month: 56

Safetensors

Model size

232B params

Tensor type

F32

BF16

F8_E4M3

Collection including amd/MiniMax-M3-MXFP4-AttnFP8

Quark Quantized MXFP4 Models

Collection

41 items • Updated 3 days ago • 1