Instructions to use 88plug/Kimi-VL-A3B-Thinking-2506-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 88plug/Kimi-VL-A3B-Thinking-2506-W4A16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="88plug/Kimi-VL-A3B-Thinking-2506-W4A16", 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("88plug/Kimi-VL-A3B-Thinking-2506-W4A16", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 88plug/Kimi-VL-A3B-Thinking-2506-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "88plug/Kimi-VL-A3B-Thinking-2506-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "88plug/Kimi-VL-A3B-Thinking-2506-W4A16",
		"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/88plug/Kimi-VL-A3B-Thinking-2506-W4A16

SGLang

How to use 88plug/Kimi-VL-A3B-Thinking-2506-W4A16 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 "88plug/Kimi-VL-A3B-Thinking-2506-W4A16" \
    --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": "88plug/Kimi-VL-A3B-Thinking-2506-W4A16",
		"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 "88plug/Kimi-VL-A3B-Thinking-2506-W4A16" \
        --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": "88plug/Kimi-VL-A3B-Thinking-2506-W4A16",
		"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 88plug/Kimi-VL-A3B-Thinking-2506-W4A16 with Docker Model Runner:
```
docker model run hf.co/88plug/Kimi-VL-A3B-Thinking-2506-W4A16
```

Kimi-VL-A3B-Thinking-2506-W4A16

W4A16 post-training quantization of moonshotai/Kimi-VL-A3B-Thinking-2506. Language-model Linear layers quantized; vision tower and merger kept BF16.

At a Glance

Property	Value
Base model	`moonshotai/Kimi-VL-A3B-Thinking-2506`
Release tier	Provisional (datafree RTN — re-quant scheduled)
Quant method	datafree RTN W4A16 (AutoRound blocked — KNOWN-FAILURES)
FLAC status	Not measured (T+7d milestone)
Quant format	compressed-tensors (Marlin G32)
Disk size	~18 GB

Quick Start

docker run --gpus device=0 -p 8080:8080 \
  vllm/vllm-openai:v0.21.0-cu129-ubuntu2404 vllm serve \
  88plug/Kimi-VL-A3B-Thinking-2506-W4A16 \
  --trust-remote-code \
  --max-model-len 8192 \
  --gpu-memory-utilization 0.90

Benchmarks

Metric	Status
Throughput (tok/s)	In progress — T+7d milestone
MMLU delta vs BF16	In progress — T+7d milestone
RULER@128k	In progress — T+30d milestone

No fabricated numbers. Results will be published to this card when measured.

License

MIT (per base model).

About

88plug AI Lab ships compressed-tensors quantizations for native vLLM v0.21.0+ deployment.

This release: Provisional tier — datafree RTN (weight-only rounding, no calibration corpus). A gold AutoRound re-quant is scheduled; 88plug architecture forbids new provisional W4A16 uploads.

Browse all releases → huggingface.co/88plug

Downloads last month: 117

Safetensors

Model size

17B params

Tensor type

BF16

Model tree for 88plug/Kimi-VL-A3B-Thinking-2506-W4A16

Base model

moonshotai/Moonlight-16B-A3B

Finetuned

moonshotai/Kimi-VL-A3B-Instruct

Finetuned

moonshotai/Kimi-VL-A3B-Thinking-2506

Quantized

(13)

this model