Instructions to use AXERA-TECH/MiniCPM-V-4.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AXERA-TECH/MiniCPM-V-4.6 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="AXERA-TECH/MiniCPM-V-4.6")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AXERA-TECH/MiniCPM-V-4.6", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AXERA-TECH/MiniCPM-V-4.6 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AXERA-TECH/MiniCPM-V-4.6" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AXERA-TECH/MiniCPM-V-4.6", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AXERA-TECH/MiniCPM-V-4.6
- SGLang
How to use AXERA-TECH/MiniCPM-V-4.6 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 "AXERA-TECH/MiniCPM-V-4.6" \ --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": "AXERA-TECH/MiniCPM-V-4.6", "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 "AXERA-TECH/MiniCPM-V-4.6" \ --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": "AXERA-TECH/MiniCPM-V-4.6", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AXERA-TECH/MiniCPM-V-4.6 with Docker Model Runner:
docker model run hf.co/AXERA-TECH/MiniCPM-V-4.6
| { | |
| "binary": "bin/axllm", | |
| "target": "AX650/AX650N aarch64", | |
| "ax_llm_branch": "ax-minicpm-v-4-6", | |
| "ax_llm_commit": "f1e288b4195c30dd7ba4e0f6fef93e850eaf838f", | |
| "simplecv_commit": "7729953c7c75ffaea441f70e0a9eb62790f3eb2b", | |
| "openai_api_cpp_commit": "f56cf8c296d1002f6602226db392325ba42f6775", | |
| "tokenizer_axera_commit": "731018211a62dcb0d606d474af9e760a0c4c44a5", | |
| "build_command": "./build.sh", | |
| "sha256": "c4ba064c0f07632274bdee7ad9d09baf2180ca85dd964d24d01c8fe22096b12a", | |
| "verified": { | |
| "date": "2026-07-06", | |
| "board": "AX650", | |
| "command": "./bin/axllm serve . --port 18080", | |
| "api_url": "http://10.168.232.217:18080/v1/chat/completions", | |
| "model": "AXERA-TECH/MiniCPM-V-4.6-AX650-C128-P1152-CTX2047", | |
| "smoke_tests": [ | |
| "text-only chat returned correct answer for 1+1", | |
| "long prompt multi-chunk prefill completed successfully", | |
| "single-image request via OpenAI-compatible API returned a valid image description", | |
| "append-only text history reused KV cache correctly", | |
| "image added after long text history reused prior text KV incrementally", | |
| "MiniCPM text, image, and video requests completed with native prefill after removing decode replay" | |
| ] | |
| } | |
| } | |