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
```

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

nm-research

Update SWE-Bench Lite eval results (official harness resolved-rate + submission-rate, vLLM 0.24.0)

f406783 verified 3 months ago

Raw History Blame Contribute Delete

6.03 kB

{
  "schema_version": "0.2.2",
  "evaluation_id": "swebench_lite_dev/RedHatAI/Kimi-K2.6-NVFP4/1784247001.8595154",
  "retrieved_timestamp": "1784247001.8595154",
  "source_metadata": {
    "source_name": "SWE-bench harness",
    "source_type": "evaluation_run",
    "source_organization_name": "RedHatAI",
    "evaluator_relationship": "first_party",
    "additional_details": {
      "note": "predictions generated with mini-swe-agent, resolved-rate scored with the official SWE-bench harness (swebench.harness.run_evaluation)"
    }
  },
  "eval_library": {
    "name": "swebench",
    "version": "4.1.0"
  },
  "model_info": {
    "name": "RedHatAI/Kimi-K2.6-NVFP4",
    "id": "RedHatAI/Kimi-K2.6-NVFP4",
    "developer": "RedHatAI",
    "inference_engine": {
      "name": "vllm",
      "version": "0.24.0"
    },
    "additional_details": {
      "profile": "kimi_nvfp4",
      "subset": "lite",
      "split": "dev"
    }
  },
  "evaluation_results": [
    {
      "evaluation_name": "swebench_lite_dev/resolved_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
      },
      "metric_config": {
        "evaluation_description": "Resolve rate: fraction of benchmark instances where the submitted patch passes verification (0.0-1.0), scored with the official SWE-bench harness.",
        "lower_is_better": false,
        "score_type": "continuous",
        "min_score": 0.0,
        "max_score": 1.0
      },
      "score_details": {
        "score": 0.21739130434782608,
        "details": {
          "total_instances": "23",
          "resolved_instances": "5",
          "submitted_instances": "23",
          "completed_instances": "19",
          "unresolved_instances": "14",
          "empty_patch_instances": "4",
          "error_instances": "0"
        },
        "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-1866",
          "pylint-dev__astroid-1978",
          "pyvista__pyvista-4315",
          "sqlfluff__sqlfluff-1517",
          "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-1625",
          "sqlfluff__sqlfluff-1733",
          "sqlfluff__sqlfluff-1763",
          "sqlfluff__sqlfluff-2419"
        ],
        "resolved_ids": [
          "marshmallow-code__marshmallow-1343",
          "pydicom__pydicom-1256",
          "pydicom__pydicom-1694",
          "pylint-dev__astroid-1268",
          "sqlfluff__sqlfluff-2419"
        ]
      },
      "generation_config": {
        "generation_args": {
          "agentic_eval_config": {
            "available_tools": [
              {
                "name": "bash"
              }
            ]
          },
          "max_attempts": 1
        }
      }
    },
    {
      "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
      },
      "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": 1.0,
        "details": {
          "total_instances": "23",
          "submitted_instances": "23",
          "unsubmitted_instances": "0"
        },
        "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-1625",
          "sqlfluff__sqlfluff-1733",
          "sqlfluff__sqlfluff-1763",
          "sqlfluff__sqlfluff-2419"
        ]
      },
      "generation_config": {
        "generation_args": {
          "agentic_eval_config": {
            "available_tools": [
              {
                "name": "bash"
              }
            ]
          },
          "max_attempts": 1
        }
      }
    }
  ]
}

	{
	"schema_version": "0.2.2",
	"evaluation_id": "swebench_lite_dev/RedHatAI/Kimi-K2.6-NVFP4/1784247001.8595154",
	"retrieved_timestamp": "1784247001.8595154",
	"source_metadata": {
	"source_name": "SWE-bench harness",
	"source_type": "evaluation_run",
	"source_organization_name": "RedHatAI",
	"evaluator_relationship": "first_party",
	"additional_details": {
	"note": "predictions generated with mini-swe-agent, resolved-rate scored with the official SWE-bench harness (swebench.harness.run_evaluation)"
	}
	},
	"eval_library": {
	"name": "swebench",
	"version": "4.1.0"
	},
	"model_info": {
	"name": "RedHatAI/Kimi-K2.6-NVFP4",
	"id": "RedHatAI/Kimi-K2.6-NVFP4",
	"developer": "RedHatAI",
	"inference_engine": {
	"name": "vllm",
	"version": "0.24.0"
	},
	"additional_details": {
	"profile": "kimi_nvfp4",
	"subset": "lite",
	"split": "dev"
	}
	},
	"evaluation_results": [
	{
	"evaluation_name": "swebench_lite_dev/resolved_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
	},
	"metric_config": {
	"evaluation_description": "Resolve rate: fraction of benchmark instances where the submitted patch passes verification (0.0-1.0), scored with the official SWE-bench harness.",
	"lower_is_better": false,
	"score_type": "continuous",
	"min_score": 0.0,
	"max_score": 1.0
	},
	"score_details": {
	"score": 0.21739130434782608,
	"details": {
	"total_instances": "23",
	"resolved_instances": "5",
	"submitted_instances": "23",
	"completed_instances": "19",
	"unresolved_instances": "14",
	"empty_patch_instances": "4",
	"error_instances": "0"
	},
	"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-1866",
	"pylint-dev__astroid-1978",
	"pyvista__pyvista-4315",
	"sqlfluff__sqlfluff-1517",
	"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-1625",
	"sqlfluff__sqlfluff-1733",
	"sqlfluff__sqlfluff-1763",
	"sqlfluff__sqlfluff-2419"
	],
	"resolved_ids": [
	"marshmallow-code__marshmallow-1343",
	"pydicom__pydicom-1256",
	"pydicom__pydicom-1694",
	"pylint-dev__astroid-1268",
	"sqlfluff__sqlfluff-2419"
	]
	},
	"generation_config": {
	"generation_args": {
	"agentic_eval_config": {
	"available_tools": [
	{
	"name": "bash"
	}
	]
	},
	"max_attempts": 1
	}
	}
	},
	{
	"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
	},
	"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": 1.0,
	"details": {
	"total_instances": "23",
	"submitted_instances": "23",
	"unsubmitted_instances": "0"
	},
	"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-1625",
	"sqlfluff__sqlfluff-1733",
	"sqlfluff__sqlfluff-1763",
	"sqlfluff__sqlfluff-2419"
	]
	},
	"generation_config": {
	"generation_args": {
	"agentic_eval_config": {
	"available_tools": [
	{
	"name": "bash"
	}
	]
	},
	"max_attempts": 1
	}
	}
	}
	]
	}