Instructions to use QuantTrio/Kimi-K3-Cubic-2.5Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantTrio/Kimi-K3-Cubic-2.5Bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="QuantTrio/Kimi-K3-Cubic-2.5Bit", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantTrio/Kimi-K3-Cubic-2.5Bit", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuantTrio/Kimi-K3-Cubic-2.5Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/Kimi-K3-Cubic-2.5Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/Kimi-K3-Cubic-2.5Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuantTrio/Kimi-K3-Cubic-2.5Bit

SGLang

How to use QuantTrio/Kimi-K3-Cubic-2.5Bit 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 "QuantTrio/Kimi-K3-Cubic-2.5Bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/Kimi-K3-Cubic-2.5Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "QuantTrio/Kimi-K3-Cubic-2.5Bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/Kimi-K3-Cubic-2.5Bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use QuantTrio/Kimi-K3-Cubic-2.5Bit with Docker Model Runner:
```
docker model run hf.co/QuantTrio/Kimi-K3-Cubic-2.5Bit
```

JunHowie commited on Aug 7

Commit

cc49249

verified ·

1 Parent(s): 9f5095f

Upload README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -24,6 +24,17 @@ Base model: [moonshotai/Kimi-K3](https://huggingface.co/moonshotai/Kimi-K3)
 **2.8T parameters · 2.5-bit experts · one 8 × H200 node · ~700K context**
 Kimi-K3-Cubic-2.5Bit is the first public showcase of **Cubic quantization**,
 exploring practical ultra-low-bit, high-concurrency LLM inference.

 **2.8T parameters · 2.5-bit experts · one 8 × H200 node · ~700K context**
+<div align="center">
+  <div style="background:#ff3f46;color:#ffffff;border-radius:8px;padding:18px 24px;margin:24px 0;font-weight:700;line-height:1.8;">
+    <p>🚨 ⚠️ We are approaching Hugging Face's free storage limit ⚠️ 🚨</p>
+    <p>As a small group of individual contributors, we currently cannot cover the additional storage costs.<br>
+    We have already released 87 models, all completely free.<br>
+    Your support would be the greatest motivation for us to keep publishing new quantized models.</p>
+    <p>☕ <a href="https://ko-fi.com/quanttrio" style="color:#ffffff;text-decoration:underline;">Support us on Ko-fi</a></p>
+    <p>Every contribution helps us pay for Hugging Face storage and keep our models freely available to everyone.</p>
+  </div>
+</div>
 Kimi-K3-Cubic-2.5Bit is the first public showcase of **Cubic quantization**,
 exploring practical ultra-low-bit, high-concurrency LLM inference.