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)

# pip install -U transformers accelerate
# 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
```

Add official Agents Last Exam evaluation results

#193

by sunyiyou - opened Oct 1

base: refs/heads/main

←

from: refs/pr/193

Discussion Files changed

+240

-0

YAML Metadata Error:Invalid Eval Result format in .eval_results/ale-kimi-code-thinking-max.yaml

Check out the documentation for more information.

Show details

✖ Invalid input: expected object, received null → at [7].dataset ✖ Invalid input: expected number, received undefined → at [7].value

Files changed (2) hide show

.eval_results/ale-claude-code-thinking-max.yaml +120 -0
.eval_results/ale-kimi-code-thinking-max.yaml +120 -0

.eval_results/ale-claude-code-thinking-max.yaml ADDED Viewed

	@@ -0,0 +1,120 @@

+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: overall-pass-rate
+  value: 26.973684210526315
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=149/152; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: overall-score
+  value: 50.72487812208666
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=149/152; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: ale-cli-pass-rate
+  value: 27.61904761904762
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=102/105; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: ale-cli-score
+  value: 52.78637305133695
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=102/105; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: near-term-pass-rate
+  value: 40.298507462686565
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=67/67; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: near-term-score
+  value: 71.59801555439591
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=67/67; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: full-spectrum-pass-rate
+  value: 23.636363636363637
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=54/55; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: full-spectrum-score
+  value: 44.940530822949675
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=54/55; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: last-exam-pass-rate
+  value: 7.894736842105263
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=36/38; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: last-exam-score
+  value: 20.49303255658983
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=claude_code; harness_variant=thinking-max; attempted=36/38; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.

.eval_results/ale-kimi-code-thinking-max.yaml ADDED Viewed

	@@ -0,0 +1,120 @@

+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: overall-pass-rate
+  value: 28.289473684210524
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=149/152; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: overall-score
+  value: 51.583231877805204
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=149/152; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: ale-cli-pass-rate
+  value: 27.61904761904762
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=102/105; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: ale-cli-score
+  value: 51.95649529905552
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=102/105; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: near-term-pass-rate
+  value: 38.80597014925373
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=66/67; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: near-term-score
+  value: 69.68586979044264
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=66/67; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: full-spectrum-pass-rate
+  value: 29.09090909090909
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=54/55; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: full-spectrum-score
+  value: 49.87405398972178
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=54/55; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: last-exam-pass-rate
+  value: 10.526315789473683
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=37/38; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.
+- dataset:
+    id: agents-last-exam/agents-last-exam
+    task_id: last-exam-score
+  value: 20.55276315873776
+  source:
+    url: https://agents-last-exam.org/leaderboard
+    name: ALE official leaderboard
+    user: agents-last-exam
+  notes: harness=kimi_code; harness_variant=thinking-max; attempted=37/38; official
+    leaderboard snapshot=2026-10-01T20:39:17.826877+00:00; values are percentages
+    (0-100); equal-task aggregation; unattempted tasks contribute zero; pass threshold
+    score>=0.999. This is an official leaderboard export, not an HF-verified evaluation.