Instructions to use moonshotai/Kimi-K2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moonshotai/Kimi-K2.5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-K2.5", 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, AutoModel

processor = AutoProcessor.from_pretrained("moonshotai/Kimi-K2.5", trust_remote_code=True)
model = AutoModel.from_pretrained("moonshotai/Kimi-K2.5", 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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moonshotai/Kimi-K2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-K2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moonshotai/Kimi-K2.5",
		"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/moonshotai/Kimi-K2.5

SGLang

How to use moonshotai/Kimi-K2.5 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 "moonshotai/Kimi-K2.5" \
    --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": "moonshotai/Kimi-K2.5",
		"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 "moonshotai/Kimi-K2.5" \
        --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": "moonshotai/Kimi-K2.5",
		"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 moonshotai/Kimi-K2.5 with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-K2.5
```

bigmoyan commited on Jan 29

Commit

6650964

verified ·

1 Parent(s): 907b3ee

Remove default system prompt, fix media_start token and update readme (#20)

Browse files

- remove default system prompt (3a2c18aa8f64e39d29a7974a686e388f7f5f6292)
- fix: should be <|media_start|> (729b62b748575b92fee4c44b03c2aca54c447cb9)
- fix: should be <|media_start|> (d1bc6a58155f947418c2e48c79978634d0ac925b)
- use media_begin because it was in 3rd party code (abb1505cb489130aec852226de64a48a9bbc3458)
- fix (2e6b74b356fe2968c1213b798d601da8311482ba)
- fix (b9d08095157e03efb215ddac3619641c09176c80)
- update README (d03fdeaffc59afeac9082ab5fa0c21362cb7bc7f)
- fix format (847724a8eb9d7a931b8978d1a5cf7d73662f9174)

Files changed (2) hide show

README.md +5 -0
chat_template.jinja +1 -5

README.md CHANGED Viewed

@@ -29,6 +29,11 @@ pipeline_tag: image-text-to-text
 <b>📰&nbsp;&nbsp;<a href="https://www.kimi.com/blog/kimi-k2-5.html">Tech Blog</a></b>
 </p>
 ## 1. Model Introduction
 Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

 <b>📰&nbsp;&nbsp;<a href="https://www.kimi.com/blog/kimi-k2-5.html">Tech Blog</a></b>
 </p>
+## 0. Changelog
+- 2026.1.29:
+    - The default system prompt might cause confusion to users and unexpected behaviours, so we remove it.
+    - The token `<|media_start|>` is incorrect; it has been replaced with `<|media_begin|>` in the chat template.
 ## 1. Model Introduction
 Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

chat_template.jinja CHANGED Viewed

@@ -5,7 +5,7 @@
     {%- elif c is not none -%}
       {% for content in c -%}
         {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
-          <|media_start|>image<|media_content|><|media_pad|><|media_end|>
         {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
           <|kimi_k25_video_placeholder|>
         {% else -%}
@@ -57,10 +57,6 @@
     <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
   {%- endif -%}
 {%- endif -%}
-{%- if messages|length == 0 or messages[0]['role'] != 'system' -%}
-  <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
-{%- endif -%}
 {%- for message in hist_msgs -%}
   {{set_roles(message)}}

     {%- elif c is not none -%}
       {% for content in c -%}
         {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
+          <|media_begin|>image<|media_content|><|media_pad|><|media_end|>
         {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
           <|kimi_k25_video_placeholder|>
         {% else -%}
     <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
   {%- endif -%}
 {%- endif -%}
 {%- for message in hist_msgs -%}
   {{set_roles(message)}}