Instructions to use luisra/Kimi-K2-Instruct-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luisra/Kimi-K2-Instruct-4bit with Transformers:

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

pipe = pipeline("text-generation", model="luisra/Kimi-K2-Instruct-4bit", 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("luisra/Kimi-K2-Instruct-4bit", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("luisra/Kimi-K2-Instruct-4bit", trust_remote_code=True, device_map="auto")
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 Settings

vLLM

How to use luisra/Kimi-K2-Instruct-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luisra/Kimi-K2-Instruct-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luisra/Kimi-K2-Instruct-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/luisra/Kimi-K2-Instruct-4bit

SGLang

How to use luisra/Kimi-K2-Instruct-4bit 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 "luisra/Kimi-K2-Instruct-4bit" \
    --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": "luisra/Kimi-K2-Instruct-4bit",
		"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 "luisra/Kimi-K2-Instruct-4bit" \
        --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": "luisra/Kimi-K2-Instruct-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use luisra/Kimi-K2-Instruct-4bit with Docker Model Runner:
```
docker model run hf.co/luisra/Kimi-K2-Instruct-4bit
```

luisra commited on Aug 9, 2025

Commit

42e7cd2

verified ·

1 Parent(s): 5a7877a

Add files using upload-large-folder tool

Browse files

Files changed (20) hide show

model-00006-of-00107.safetensors +3 -0
model-00013-of-00107.safetensors +3 -0
model-00014-of-00107.safetensors +3 -0
model-00016-of-00107.safetensors +3 -0
model-00019-of-00107.safetensors +3 -0
model-00021-of-00107.safetensors +3 -0
model-00023-of-00107.safetensors +3 -0
model-00026-of-00107.safetensors +3 -0
model-00038-of-00107.safetensors +3 -0
model-00043-of-00107.safetensors +3 -0
model-00065-of-00107.safetensors +3 -0
model-00070-of-00107.safetensors +3 -0
model-00079-of-00107.safetensors +3 -0
model-00085-of-00107.safetensors +3 -0
model-00092-of-00107.safetensors +3 -0
model-00100-of-00107.safetensors +3 -0
model-00102-of-00107.safetensors +3 -0
model-00105-of-00107.safetensors +3 -0
model-00107-of-00107.safetensors +3 -0
model.safetensors.index.json +1 -1

model-00006-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a38fb9b36085089a9653ef663cf231ac2109e8ee27c57e5662c9d9a6b4d5b6
+size 4996629442

model-00013-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:20cc428e9beeb6529de5d61f9837374ea6f080cb43dc3865b18b0e84e3117bb0
+size 4996629624

model-00014-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:792301952cf321895a5f95fe3561a2c1448a5efc4933c3ec72aef48ec2fd76d6
+size 4999514217

model-00016-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b36c6ed56e9e787b51b9704b354032f26c9e433d5b7d96b79aac36176edc842
+size 4999515144

model-00019-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e302c9e44841a4ea7e0e7ed0212b59ce79547b16ca2d25010b63e359ed90c680
+size 4996632293

model-00021-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ccff52b852bff5e492f15c3757f1db8159915b2c9eef5e4cf66de851bc5205ff
+size 4999517981

model-00023-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:236a209a1d16fda94f70f7b3779d5c52b4fd80dc1729f56cb0f39260edfa9b24
+size 4999518902

model-00026-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:50d291962c32c8219206a64beb701b0d4aa99d50ba86758597400a32b9b31184
+size 4996632290

model-00038-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:af3cb52f71f8c9ab8db63b87cdd51aa63741b5b552643766cbbcb29c3506c2d1
+size 4996632292

model-00043-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:35ed03d88b951cf58ae80d835fa541881c04de3ddf5d9c17072bd617b3f40ebb
+size 4996633384

model-00065-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c12536ea9fd0fbe2b20c9efa249ea38de9137c2e85d782eab9b34814d0faf937
+size 4999517708

model-00070-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:46f4072b3d4edcffae5031b00a2ce1238ac4ccba723e822df7a666907d3c8fd1
+size 4996632298

model-00079-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:20c69049ee2776caa8ba76c4d47c5dc3784786fb4cfe15f87f70082979ac0f3b
+size 4996632287

model-00085-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a43210a14b4ed95eee5a9736c25bc65fcb3ceed1cd2e306a9560067bdbe65fae
+size 4999519442

model-00092-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f61e364bc2fc1df5b7f32a0077cd017017970a1e5bdc70437a33c398c1bf91fd
+size 4999519443

model-00100-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5253b4c5e174955f8157b0b2420038728e6ec283b0cc518d11b99e3ddd28a4f
+size 4996632285

model-00102-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8e20768e77775563140e3c291c8a4f8ec864eaa2ecd4ef3ff9ae6a5d95978f
+size 4999517678

model-00105-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:57a0d6b44eba9c800c3a606987408be6527bd1fe0a362964614f03f6619b3e8e
+size 4996632289

model-00107-of-00107.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8db7ed764d65a18eb7ddbad76d070b43236d98f2ab7a7ec2df0ed399f85a21
+size 3589089021

model.safetensors.index.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e4b40b1f13d94ac4b7f76e9fcd909f5cd35dae834bc465fba3e53f6b2f531d9
 size 43419708

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1b1544ec27d5125df4f7862fb1677925fdaaca77f31b5400f0b09aed03e517a
 size 43419708