Instructions to use openbmb/MiniCPM-V-4.6-Thinking-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps

How to use openbmb/MiniCPM-V-4.6-Thinking-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM-V-4.6-Thinking-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM-V-4.6-Thinking-GPTQ",
		"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/openbmb/MiniCPM-V-4.6-Thinking-GPTQ

SGLang

How to use openbmb/MiniCPM-V-4.6-Thinking-GPTQ 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 "openbmb/MiniCPM-V-4.6-Thinking-GPTQ" \
    --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": "openbmb/MiniCPM-V-4.6-Thinking-GPTQ",
		"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 "openbmb/MiniCPM-V-4.6-Thinking-GPTQ" \
        --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": "openbmb/MiniCPM-V-4.6-Thinking-GPTQ",
		"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 openbmb/MiniCPM-V-4.6-Thinking-GPTQ with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-V-4.6-Thinking-GPTQ
```

tc-mb commited on 2 days ago

Commit

8846a79

verified ·

1 Parent(s): 44318b7

update readme

Browse files

Files changed (1) hide show

README.md +1 -14

README.md CHANGED Viewed

@@ -15,20 +15,7 @@ A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Ph
 ## MiniCPM-V 4.6 Thinking
-**MiniCPM-V 4.6 Thinking** is the long chain-of-thought reasoning variant of [MiniCPM-V 4.6](https://huggingface.co/openbmb/MiniCPM-V-4.6). It generates an explicit reasoning trace before producing the final answer, substantially boosting performance on complex multimodal reasoning, math, and OCR-heavy tasks, while keeping the same edge-friendly architecture (SigLIP2-400M vision encoder + Qwen3.5-0.8B LLM) and the mixed 4x/16x visual token compression of MiniCPM-V 4.6. Notable features of MiniCPM-V 4.6 Thinking include:
-- 🔥 **Leading Foundation Capability.**
-  MiniCPM-V 4.6 scores 13 on the Artificial Analysis Intelligence Index benchmark, outperforming Qwen3.5-0.8B's score of 10 with 19x fewer token cost, and Qwen3.5-0.8B-Thinking's score of 11 with 43x fewer token cost. It also surpasses the larger Ministral 3 3B (score of 11).
-- 💪 **Strong Multimodal Capability.**
-  MiniCPM-V 4.6 outperforms Qwen3.5-0.8B on most vision-language understanding tasks, and reaches Qwen3.5 2B-level capability on many benchmarks including OpenCompass, RefCOCO, HallusionBench, MUIRBench, and OCRBench.
-- 🚀 **Ultra-Efficient Architecture.**
-  Based on the latest technique in [LLaVA-UHD v4](https://github.com/THUMAI-Lab/LLaVA-UHD-v4), MiniCPM-V 4.6 reduces the visual encoding computation FLOPs by more than 50%. It enables MiniCPM-V 4.6 to achieve better efficiency to even smaller models, achieving ~1.5x token throughput compared to Qwen3.5-0.8B.
-  It also supports mixed 4x/16x visual token compression rate, allowing flexible switching between accuracy and speed.
-- 📱 **Broad Mobile Platform Coverage.**
-  MiniCPM-V 4.6 can be deployed across all three mainstream mobile platforms — iOS, Android, and HarmonyOS. With every edge adaptation code open-sourced, developers can reproduce the on-device experience in [just a few steps](#deploy-minicpm-v-46-on-ios-android-and-harmonyos-platforms).
-- 🛠️ **Developer Friendly.**
-  MiniCPM-V 4.6 is adapted to [inference frameworks](#use-minicpm-v-46-in-other-inference-and-training-frameworks) such as vLLM, SGLang, llama.cpp, Ollama, and supports [fine-tuning ecosystems](#use-minicpm-v-46-in-other-inference-and-training-frameworks) such as SWIFT and LLaMA-Factory. Developers can quickly customize models for new domains and tasks on consumer-grade GPUs. We provide multiple quantized variants across GGUF, BNB, AWQ, and GPTQ formats.
 ### Evaluation <!-- omit in toc -->

 ## MiniCPM-V 4.6 Thinking
+**MiniCPM-V 4.6 Thinking** is the long chain-of-thought reasoning variant of [MiniCPM-V 4.6](https://huggingface.co/openbmb/MiniCPM-V-4.6). It generates an explicit reasoning trace before producing the final answer, substantially boosting performance on complex multimodal reasoning, math, and OCR-heavy tasks, while keeping the same edge-friendly architecture (SigLIP2-400M vision encoder + Qwen3.5-0.8B LLM) and the mixed 4x/16x visual token compression of MiniCPM-V 4.6.
 ### Evaluation <!-- omit in toc -->