Instructions to use moonshotai/Kimi-K3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moonshotai/Kimi-K3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-K3", 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 AutoModel
model = AutoModel.from_pretrained("moonshotai/Kimi-K3", trust_remote_code=True, device_map="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moonshotai/Kimi-K3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-K3"
# 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-K3",
		"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-K3

SGLang

How to use moonshotai/Kimi-K3 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-K3" \
    --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-K3",
		"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-K3" \
        --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-K3",
		"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-K3 with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-K3
```

zli12321 commited on 4 days ago

Commit

b1bd23b

verified ·

1 Parent(s): 9f62e4e

Add LHTB (Long-Horizon Terminal-Bench) eval result: 37.8

Browse files

Adds the **Long-Horizon Terminal-Bench (LHTB)** result for Kimi K3 so it appears on the [LHTB benchmark leaderboard](https://huggingface.co/datasets/IntelligenceLab/Long-Horizon-Terminal-Bench).

**Score: 37.8** (mean reward x100 over 46 tasks, partial credit)

| Metric | Value |
|---|---|
| Mean reward (46 tasks) | 0.3778 |
| Solved (reward >= 0.95) | 6 / 46 |
| Perfect (reward = 1.0) | 5 / 46 |
| Agent | terminus-2 (official LHTB Harbor harness) |
| Budget | 90 min per task, 1 trial per task |

LHTB measures how well agents sustain useful work in a containerized terminal
over hundreds of steps, graded by hidden rebuild-from-artifact verifiers. This
places Kimi K3 2nd among open-weight models currently on the board.

Complete run artifacts (per-trial configs, results, verifier outputs and terminal
recordings) are published so the score can be audited without rerunning the suite:
https://huggingface.co/datasets/IntelligenceLab/LHTB-leaderboard/tree/main/submissions/long-horizon-terminal-bench/1.0/terminus-2__api_moonshot_kimi-k3

Submitted by the LHTB maintainers; happy to adjust the formatting or withdraw if you prefer.

Files changed (1) hide show

.eval_results/lhtb.yaml +9 -0

.eval_results/lhtb.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: IntelligenceLab/Long-Horizon-Terminal-Bench
+    task_id: lhtb
+  value: 37.8
+  date: '2026-07-22'
+  source:
+    url: https://zli12321.github.io/LHTB/leaderboard.html
+    name: LHTB leaderboard
+  notes: "mean reward x100 over 46 tasks (partial credit); solved@0.95=6/46; official LHTB Harbor harness"