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

Libraries

How to use unsloth/Kimi-K2-Thinking with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/Kimi-K2-Thinking", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/Kimi-K2-Thinking", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("unsloth/Kimi-K2-Thinking", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/Kimi-K2-Thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Kimi-K2-Thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Kimi-K2-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Kimi-K2-Thinking

SGLang

How to use unsloth/Kimi-K2-Thinking 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 "unsloth/Kimi-K2-Thinking" \
    --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": "unsloth/Kimi-K2-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "unsloth/Kimi-K2-Thinking" \
        --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": "unsloth/Kimi-K2-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use unsloth/Kimi-K2-Thinking with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/Kimi-K2-Thinking to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/Kimi-K2-Thinking to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/Kimi-K2-Thinking to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/Kimi-K2-Thinking",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/Kimi-K2-Thinking with Docker Model Runner:
```
docker model run hf.co/unsloth/Kimi-K2-Thinking
```

danielhanchen commited on Nov 7, 2025

Commit

41290ed

verified ·

1 Parent(s): 1fb62a9

Add files using upload-large-folder tool

Browse files

Files changed (30) hide show

model-00010-of-000062.safetensors +3 -0
model-00012-of-000062.safetensors +3 -0
model-00013-of-000062.safetensors +3 -0
model-00014-of-000062.safetensors +3 -0
model-00016-of-000062.safetensors +3 -0
model-00019-of-000062.safetensors +3 -0
model-00020-of-000062.safetensors +3 -0
model-00021-of-000062.safetensors +3 -0
model-00022-of-000062.safetensors +3 -0
model-00023-of-000062.safetensors +3 -0
model-00026-of-000062.safetensors +3 -0
model-00028-of-000062.safetensors +3 -0
model-00029-of-000062.safetensors +3 -0
model-00032-of-000062.safetensors +3 -0
model-00033-of-000062.safetensors +3 -0
model-00034-of-000062.safetensors +3 -0
model-00035-of-000062.safetensors +3 -0
model-00037-of-000062.safetensors +3 -0
model-00038-of-000062.safetensors +3 -0
model-00041-of-000062.safetensors +3 -0
model-00043-of-000062.safetensors +3 -0
model-00046-of-000062.safetensors +3 -0
model-00048-of-000062.safetensors +3 -0
model-00049-of-000062.safetensors +3 -0
model-00050-of-000062.safetensors +3 -0
model-00051-of-000062.safetensors +3 -0
model-00053-of-000062.safetensors +3 -0
model-00054-of-000062.safetensors +3 -0
model-00057-of-000062.safetensors +3 -0
model-00058-of-000062.safetensors +3 -0

model-00010-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f3885c59a40662088e37b4bee49cdd33428cd40ca18f165405cda7806f4931de
+size 9808995784

model-00012-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:766eb3b51f5bf5aeb99f6a7c61f83b56516dc9fcc2b94a7cb9b999b23e7215dd
+size 9808999256

model-00013-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca1661d9843460f63870282cbbe22a68768a7d7bddf5a983a430249ed8e4724a
+size 9808999256

model-00014-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:855acdcee579c79e463c9e3f2dd8a35b7ed0c4109c387e4a5780987e7c98d6a3
+size 9808999256

model-00016-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca84d3d21a5fcde572ea00447a30fb6174107f9dcb13c994ba6540717056620c
+size 9808999256

model-00019-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6695243bd3ce55705e384ef51be993ba6b881ddbff841510be7937141b05761d
+size 9808999256

model-00020-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e84f956e805f92ba224da76e5adc8f4303e5b66b7ac82aa2b793517c0f7bb1a3
+size 9808999256

model-00021-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed0c3abc1898eb36cacdcf152f6d22f244dd8f95ec3e597a406575ef936e12c
+size 9808999256

model-00022-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:96ce2ddc9ff80d522e57437c123147066593e429523e1a24b0e5b134b8af5030
+size 9808999256

model-00023-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc62e7fcd8184cd45c046e2f92f2abde6009c160b7b0cd57da536af38e66d771
+size 9808999256

model-00026-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a16fe7a9816d71e5927fc93e229aef8821a37ca2382700ef9878c4b72cb9ee34
+size 9808999256

model-00028-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:10ef5c61dacb9c0390dd5e783a82d10bbaf25b1ff5d1cb2f1bbfe0a59b14d0cd
+size 9808999256

model-00029-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f694289ad0f5c42dbcbcec326a8d2286f3b989e8c72a23c79cab8145ce4411d7
+size 9808999256

model-00032-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd98998e2379b38f7ac412df3a1a129e1620cd3c76d97fa0366d92cad984c02
+size 9808999256

model-00033-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:45a2dcd2e1ffd907e820d2721bfa53be572c0048d8c6d1a1c4de7039daacea91
+size 9808999256

model-00034-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1cda7176b5651e3a3be960058f2e9ccdb965680c469a241b9169bcca7e861abf
+size 9808999256

model-00035-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcd19675824aa0741579ecf437ffe37f6ee17a2064f58fb196f5b20bd587161
+size 9808999256

model-00037-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:562593af7257c91cdfc5662ab1c46d3f7bba61ffe0d233c9958f70e357c28466
+size 9808999256

model-00038-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d2c8ab656a35fac21c1654b7ac4f64654a4318f52ca0d27c4e24352f5eda50
+size 9808999256

model-00041-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91c07e51cf58dca947f0bd8ac63615b0878d5f9e202f966855bf07e255dc3f9a
+size 9808999256

model-00043-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ede8d1839e19c8acdc5f3fd2a7c43a18f49ccd1243115169b99dd0b556d0ca0
+size 9808999256

model-00046-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a5188a70ebf7134f241450f93030e64fe9fa4d0f1f42f965cef1deab9b53c7a1
+size 9808999256

model-00048-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9226c9c424c089a18d7fda321fe90b04e0c607b48f193e5647f1cda87423e69e
+size 9808999256

model-00049-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c10121535372dc5add3f07c1becdb580b2a8b672e51d3382c347900fcacd3466
+size 9808999256

model-00050-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b09203a76184ec1f6b080445903842ebdc3471c5b41d654f64cf511956f8e694
+size 9808999256

model-00051-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bdbda5bb8ff9d2872cab62f0dd6c15d23ec655a388a34c78347904077ba0dc9e
+size 9808999256

model-00053-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e4754ee3f4f9376f3b1c1795bf712f6269fbe6e9cb62cd7edd5f58c684ecfd3a
+size 9808999256

model-00054-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a8c98b6317e08d5f2364e671848c82a451b0b8d1ab60f5d6172f6aa38b92a5
+size 9808999256

model-00057-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:be21402538fcac79716f15c41d3f7fc69569d45d8e0211daaf2b19685411ddf0
+size 9808999256

model-00058-of-000062.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3c04f279972453f97c61c1acd9973154dba89a9e21d325950bab5116e13cf6
+size 9808999256