Instructions to use amd/Kimi-K2-Thinking-W4A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/Kimi-K2-Thinking-W4A8 with Transformers:

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

pipe = pipeline("text-generation", model="amd/Kimi-K2-Thinking-W4A8", 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("amd/Kimi-K2-Thinking-W4A8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("amd/Kimi-K2-Thinking-W4A8", 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 amd/Kimi-K2-Thinking-W4A8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/Kimi-K2-Thinking-W4A8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Kimi-K2-Thinking-W4A8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/Kimi-K2-Thinking-W4A8

SGLang

How to use amd/Kimi-K2-Thinking-W4A8 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 "amd/Kimi-K2-Thinking-W4A8" \
    --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": "amd/Kimi-K2-Thinking-W4A8",
		"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 "amd/Kimi-K2-Thinking-W4A8" \
        --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": "amd/Kimi-K2-Thinking-W4A8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/Kimi-K2-Thinking-W4A8 with Docker Model Runner:
```
docker model run hf.co/amd/Kimi-K2-Thinking-W4A8
```

Model Overview

Model Architecture: Kimi-K2-Thinking
- Input: Text
- Output: Text
Supported Hardware Microarchitecture: AMD MI300/MI355
ROCm: 7.0
PyTorch: 2.8.0
Transformers: 4.53.0
Operating System(s): Linux
Inference Engine: vLLM
Model Optimizer: AMD-Quark (V0.10)
- Weight quantization: INT4 Per-Channel & FP8E4M3, Static
- Activation quantization: FP8E4M3, Dynamic

This model was built with moonshotai Kimi-K2-Thinking model by applying AMD-Quark for INT4-FP8 quantization.

Model Quantization

The model was quantized from moonshotai/Kimi-K2-Thinking using AMD-Quark.

Deployment

This model can be deployed efficiently using the vLLM backends.

Evaluation

The model was evaluated on GSM8K benchmarks using the lm-evaluation-harness framework.

Accuracy

Benchmark	Kimi-K2-Thinking	Kimi-K2-Thinking-W4A8(this model)	Recovery
GSM8K	93.93	93.4	99.4%

Reproduction

The results of GSM8K were obtained using lm-evaluation-harness and latest vLLM.

Launch vLLM

MODEL_DIR=/data/amd/Kimi-K2-Thinking-W4A8
VLLM_ATTENTION_BACKEND="TRITON_MLA" VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=0 VLLM_ROCM_USE_AITER_FP4BMM=0 vllm serve $MODEL_DIR \
    --port 8001 \
    --trust-remote-code \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --load-format "fastsafetensors"

GSM8K evaluation

MODEL_ARGS="model=/data/amd/Kimi-K2-Thinking-W4A8,base_url=http://localhost:8001/v1/completions,num_concurrent=999999,timeout=999999,tokenized_requests=False,max_length=38768,temperature=0.6,top_p=0.95,add_bos_token=True,seed=$SEED,trust_remote_code=True"
lm_eval \
    --model local-completions \
    --model_args $MODEL_ARGS \
    --tasks gsm8k \
    --num_fewshot 8 \
    --batch_size auto

License

Downloads last month: 49

Model tree for amd/Kimi-K2-Thinking-W4A8

Base model

moonshotai/Kimi-K2-Thinking

Quantized

(19)

this model