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)

# 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)
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=40)
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
```

Kimi-K2.6-NVFP4 / every_eval_ever /swebench_lite_dev.json

nm-research

Add BFCL v4 and SWE-bench Lite EveryEvalEver results

ce29fe8 verified 4 days ago

Raw

History Blame Contribute Delete

5.64 kB

	{
	"schema_version": "0.2.2",
	"evaluation_id": "swebench_lite_dev/RedHatAI/Kimi-K2.6-NVFP4/1782913700",
	"retrieved_timestamp": "1782913700",
	"source_metadata": {
	"source_name": "mini-swe-agent",
	"source_type": "evaluation_run",
	"source_organization_name": "RedHatAI",
	"evaluator_relationship": "third_party",
	"additional_details": {
	"note": "submission-rate aggregation across reruns"
	}
	},
	"eval_library": {
	"name": "mini-swe-agent",
	"version": "2.4.3"
	},
	"model_info": {
	"name": "RedHatAI/Kimi-K2.6-NVFP4",
	"id": "RedHatAI/Kimi-K2.6-NVFP4",
	"developer": "RedHatAI",
	"inference_engine": {
	"name": "vllm",
	"version": "0.22.1"
	},
	"additional_details": {
	"profile": "kimi_nvfp4",
	"subset": "lite",
	"split": "dev"
	}
	},
	"evaluation_results": [
	{
	"evaluation_name": "swebench_lite_dev/submission_rate",
	"source_data": {
	"dataset_name": "SWE-bench Lite dev",
	"source_type": "hf_dataset",
	"hf_repo": "princeton-nlp/SWE-Bench_Lite",
	"hf_split": "dev",
	"samples_number": 23,
	"sample_ids": [
	"marshmallow-code__marshmallow-1343",
	"marshmallow-code__marshmallow-1359",
	"pvlib__pvlib-python-1072",
	"pvlib__pvlib-python-1154",
	"pvlib__pvlib-python-1606",
	"pvlib__pvlib-python-1707",
	"pvlib__pvlib-python-1854",
	"pydicom__pydicom-1139",
	"pydicom__pydicom-1256",
	"pydicom__pydicom-1413",
	"pydicom__pydicom-1694",
	"pydicom__pydicom-901",
	"pylint-dev__astroid-1196",
	"pylint-dev__astroid-1268",
	"pylint-dev__astroid-1333",
	"pylint-dev__astroid-1866",
	"pylint-dev__astroid-1978",
	"pyvista__pyvista-4315",
	"sqlfluff__sqlfluff-1517",
	"sqlfluff__sqlfluff-1625",
	"sqlfluff__sqlfluff-1733",
	"sqlfluff__sqlfluff-1763",
	"sqlfluff__sqlfluff-2419"
	]
	},
	"metric_config": {
	"evaluation_description": "Submission rate (Submitted / total instances).",
	"lower_is_better": false,
	"score_type": "continuous",
	"min_score": 0.0,
	"max_score": 1.0
	},
	"score_details": {
	"score": 0.9130434782608695,
	"details": {
	"total_instances": "23",
	"submitted_instances": "21",
	"unsubmitted_instances": "2",
	"status_counts": "{\"RepeatedFormatError\": 2, \"Submitted\": 21}",
	"unsubmitted_ids": "[\"sqlfluff__sqlfluff-1625\", \"sqlfluff__sqlfluff-1733\"]",
	"source_exit_status_files": "[\"/home/shubhra/kimik2.6_evals/runs/swebench/20260629T171225Z_kimi_nvfp4_lite_dev/output/exit_statuses_1782760165.6381476.yaml\", \"/home/shubhra/kimik2.6_evals/runs/swebench/20260630T135435Z_kimi_nvfp4_lite_dev/output/exit_statuses_1782827902.5985954.yaml\", \"/home/shubhra/kimik2.6_evals/runs/swebench/20260630T141107Z_kimi_nvfp4_lite_dev/output/exit_statuses_1782830121.1086848.yaml\", \"/home/shubhra/kimik2.6_evals/runs/swebench/20260630T151900Z_kimi_nvfp4_lite_dev/output/exit_statuses_1782833877.9161725.yaml\", \"/home/shubhra/kimik2.6_evals/runs/swebench/20260630T190648Z_kimi_nvfp4_lite_dev/output/exit_statuses_1782846629.8118455.yaml\", \"/home/shubhra/kimik2.6_evals/runs/swebench/20260630T192452Z_kimi_nvfp4_lite_dev/output/exit_statuses_1782848479.344266.yaml\", \"/home/shubhra/kimik2.6_evals/runs/swebench/20260630T195651Z_kimi_nvfp4_lite_dev/output/exit_statuses_1782850223.0775344.yaml\"]"
	},
	"completed_ids": [
	"marshmallow-code__marshmallow-1343",
	"marshmallow-code__marshmallow-1359",
	"pvlib__pvlib-python-1072",
	"pvlib__pvlib-python-1154",
	"pvlib__pvlib-python-1606",
	"pvlib__pvlib-python-1707",
	"pvlib__pvlib-python-1854",
	"pydicom__pydicom-1139",
	"pydicom__pydicom-1256",
	"pydicom__pydicom-1413",
	"pydicom__pydicom-1694",
	"pydicom__pydicom-901",
	"pylint-dev__astroid-1196",
	"pylint-dev__astroid-1268",
	"pylint-dev__astroid-1333",
	"pylint-dev__astroid-1866",
	"pylint-dev__astroid-1978",
	"pyvista__pyvista-4315",
	"sqlfluff__sqlfluff-1517",
	"sqlfluff__sqlfluff-1625",
	"sqlfluff__sqlfluff-1733",
	"sqlfluff__sqlfluff-1763",
	"sqlfluff__sqlfluff-2419"
	],
	"submitted_ids": [
	"marshmallow-code__marshmallow-1343",
	"marshmallow-code__marshmallow-1359",
	"pvlib__pvlib-python-1072",
	"pvlib__pvlib-python-1154",
	"pvlib__pvlib-python-1606",
	"pvlib__pvlib-python-1707",
	"pvlib__pvlib-python-1854",
	"pydicom__pydicom-1139",
	"pydicom__pydicom-1256",
	"pydicom__pydicom-1413",
	"pydicom__pydicom-1694",
	"pydicom__pydicom-901",
	"pylint-dev__astroid-1196",
	"pylint-dev__astroid-1268",
	"pylint-dev__astroid-1333",
	"pylint-dev__astroid-1866",
	"pylint-dev__astroid-1978",
	"pyvista__pyvista-4315",
	"sqlfluff__sqlfluff-1517",
	"sqlfluff__sqlfluff-1763",
	"sqlfluff__sqlfluff-2419"
	]
	},
	"generation_config": {
	"generation_args": {
	"agentic_eval_config": {
	"available_tools": [
	{
	"name": "bash"
	}
	]
	},
	"max_attempts": 1
	}
	}
	}
	]
	}