Instructions to use RedHatAI/Kimi-K2.6-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Kimi-K2.6-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/Kimi-K2.6-NVFP4", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModel

processor = AutoProcessor.from_pretrained("RedHatAI/Kimi-K2.6-NVFP4", trust_remote_code=True)
model = AutoModel.from_pretrained("RedHatAI/Kimi-K2.6-NVFP4", trust_remote_code=True, device_map="auto")
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?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Kimi-K2.6-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Kimi-K2.6-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Kimi-K2.6-NVFP4",
		"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/RedHatAI/Kimi-K2.6-NVFP4

SGLang

How to use RedHatAI/Kimi-K2.6-NVFP4 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 "RedHatAI/Kimi-K2.6-NVFP4" \
    --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": "RedHatAI/Kimi-K2.6-NVFP4",
		"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 "RedHatAI/Kimi-K2.6-NVFP4" \
        --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": "RedHatAI/Kimi-K2.6-NVFP4",
		"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 RedHatAI/Kimi-K2.6-NVFP4 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Kimi-K2.6-NVFP4
```

nm-research commited on Jul 1

Commit

07c3070

verified ·

1 Parent(s): 6012a1b

Clarify BFCL accuracy vs SWE submission coverage

Browse files

Files changed (1) hide show

README.md +8 -2

README.md CHANGED Viewed

@@ -130,7 +130,7 @@ We evaluated this model with [lm-evaluation-harness](https://github.com/Eleuther
     <tr><td>IFEval (instruction-level strict, avg@3)</td><td>95.96%</td></tr>
     <tr>
-      <td rowspan="6">Agentic and tool use</td>
       <td>BFCL v4 non_live</td>
       <td>86.48%</td>
     </tr>
@@ -138,10 +138,16 @@ We evaluated this model with [lm-evaluation-harness](https://github.com/Eleuther
     <tr><td>BFCL v4 multi_turn</td><td>63.75%</td></tr>
     <tr><td>BFCL v4 memory</td><td>64.95%</td></tr>
     <tr><td>BFCL v4 web_search</td><td>42.00%</td></tr>
-    <tr><td>SWE-Bench Lite dev submission rate</td><td>91.30% (21/23 submitted)</td></tr>
   </tbody>
 </table>
 ### Historical preliminary check
 | Benchmark | Base model (`moonshotai/Kimi-K2.6`) | This model |

     <tr><td>IFEval (instruction-level strict, avg@3)</td><td>95.96%</td></tr>
     <tr>
+      <td rowspan="5">Agentic function calling (accuracy)</td>
       <td>BFCL v4 non_live</td>
       <td>86.48%</td>
     </tr>
     <tr><td>BFCL v4 multi_turn</td><td>63.75%</td></tr>
     <tr><td>BFCL v4 memory</td><td>64.95%</td></tr>
     <tr><td>BFCL v4 web_search</td><td>42.00%</td></tr>
+    <tr>
+      <td>Agentic coding (submission coverage)</td>
+      <td>SWE-Bench Lite dev submission rate</td>
+      <td>91.30% (21/23 submitted)</td>
+    </tr>
   </tbody>
 </table>
+BFCL rows report category accuracy. The SWE-Bench Lite row reports submission coverage (submitted runs / total instances), not final pass rate.
 ### Historical preliminary check
 | Benchmark | Base model (`moonshotai/Kimi-K2.6`) | This model |