Instructions to use moonshotai/Kimi-K2.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moonshotai/Kimi-K2.6 with Transformers:

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

pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-K2.6", 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-K2.6", trust_remote_code=True, dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moonshotai/Kimi-K2.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-K2.6"
# 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-K2.6",
		"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-K2.6

SGLang

How to use moonshotai/Kimi-K2.6 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 "moonshotai/Kimi-K2.6" \
    --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-K2.6",
		"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-K2.6" \
        --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-K2.6",
		"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-K2.6 with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-K2.6
```

bigeagle

SaylorTwift HF Staff commited on Apr 20

Commit

d9cb81b

1 Parent(s): 36d7872

Add evaluation results for HLE, GPQA, AIME, HMMT, SWE-Bench, and Terminal-Bench (#4)

Browse files

- Add evaluation results for HLE, GPQA, AIME, HMMT, SWE-Bench, and Terminal-Bench (64ed7450cf8801fae6fc24d6bea85e034393d974)

Co-authored-by: Nathan Habib <[email protected]>

Files changed (8) hide show

.eval_results/aime_2026.yaml +9 -0
.eval_results/gpqa_diamond.yaml +9 -0
.eval_results/hle.yaml +9 -0
.eval_results/hle_with_tools.yaml +10 -0
.eval_results/hmmt_feb_2026.yaml +9 -0
.eval_results/swe_bench_pro.yaml +9 -0
.eval_results/swe_bench_verified.yaml +9 -0
.eval_results/terminal_bench_2.yaml +9 -0

.eval_results/aime_2026.yaml ADDED Viewed

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

+- dataset:
+    id: MathArena/aime_2026
+    task_id: MathArena/aime_2026
+  value: 96.4
+  date: '2026-04-20'
+  source:
+    url: https://huggingface.co/moonshotai/Kimi-K2.6
+    name: Model Card
+    user: SaylorTwift

.eval_results/gpqa_diamond.yaml ADDED Viewed

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

+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 90.5
+  date: '2026-04-20'
+  source:
+    url: https://huggingface.co/moonshotai/Kimi-K2.6
+    name: Model Card
+    user: SaylorTwift

.eval_results/hle.yaml ADDED Viewed

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

+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 34.7
+  date: '2026-04-20'
+  source:
+    url: https://huggingface.co/moonshotai/Kimi-K2.6
+    name: Model Card
+    user: SaylorTwift

.eval_results/hle_with_tools.yaml ADDED Viewed

	@@ -0,0 +1,10 @@

+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 54.0
+  date: '2026-04-20'
+  source:
+    url: https://huggingface.co/moonshotai/Kimi-K2.6
+    name: Model Card
+    user: SaylorTwift
+  notes: "With tools"

.eval_results/hmmt_feb_2026.yaml ADDED Viewed

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

+- dataset:
+    id: MathArena/hmmt_feb_2026
+    task_id: MathArena/hmmt_feb_2026
+  value: 92.7
+  date: '2026-04-20'
+  source:
+    url: https://huggingface.co/moonshotai/Kimi-K2.6
+    name: Model Card
+    user: SaylorTwift

.eval_results/swe_bench_pro.yaml ADDED Viewed

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

+- dataset:
+    id: ScaleAI/SWE-bench_Pro
+    task_id: SWE_Bench_Pro
+  value: 58.6
+  date: '2026-04-20'
+  source:
+    url: https://huggingface.co/moonshotai/Kimi-K2.6
+    name: Model Card
+    user: SaylorTwift

.eval_results/swe_bench_verified.yaml ADDED Viewed

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

+- dataset:
+    id: SWE-bench/SWE-bench_Verified
+    task_id: swe_bench_%_resolved
+  value: 80.2
+  date: '2026-04-20'
+  source:
+    url: https://huggingface.co/moonshotai/Kimi-K2.6
+    name: Model Card
+    user: SaylorTwift

.eval_results/terminal_bench_2.yaml ADDED Viewed

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

+- dataset:
+    id: harborframework/terminal-bench-2.0
+    task_id: terminalbench_2
+  value: 66.7
+  date: '2026-04-20'
+  source:
+    url: https://huggingface.co/moonshotai/Kimi-K2.6
+    name: Model Card
+    user: SaylorTwift