Instructions to use gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="gitcommit90/SenseNova-Loop-9B-Preview-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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("gitcommit90/SenseNova-Loop-9B-Preview-NVFP4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gitcommit90/SenseNova-Loop-9B-Preview-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": "gitcommit90/SenseNova-Loop-9B-Preview-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/gitcommit90/SenseNova-Loop-9B-Preview-NVFP4

SGLang

How to use gitcommit90/SenseNova-Loop-9B-Preview-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 "gitcommit90/SenseNova-Loop-9B-Preview-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": "gitcommit90/SenseNova-Loop-9B-Preview-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 "gitcommit90/SenseNova-Loop-9B-Preview-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": "gitcommit90/SenseNova-Loop-9B-Preview-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 gitcommit90/SenseNova-Loop-9B-Preview-NVFP4 with Docker Model Runner:
```
docker model run hf.co/gitcommit90/SenseNova-Loop-9B-Preview-NVFP4
```

SenseNova-Loop-9B-Preview-NVFP4 / evaluation /perf_sglang_nvfp4_v1_mtp.json

gitcommit90

NVFP4 (ModelOpt) quantization of sensenova/SenseNova-Loop-9B-Preview @27abea77 with BF16 MTP head

a57aa9f verified 1 day ago

Raw History Blame Contribute Delete

4.61 kB

{
  "label": "",
  "model": "sensenova-loop-nvfp4",
  "base_url": "http://127.0.0.1:30080/v1",
  "host": "tux",
  "time": "2026-10-30T17:21:08-0700",
  "config": {
    "base_url": "http://127.0.0.1:30080/v1",
    "model": "sensenova-loop-nvfp4",
    "concurrency": "1,2,4,8",
    "num_requests": 8,
    "warmup": 2,
    "input_tokens": 1024,
    "output_tokens": 256,
    "tokenizer": "upstream/SenseNova-Loop-9B-Preview/tokenizer.json",
    "allow_prefix_cache": false,
    "no_ignore_eos": false,
    "timeout": 600,
    "label": "",
    "out": "eval/runs/perf_sglang_nvfp4_v1_mtp.json",
    "prompt_text_tokens": 1024,
    "prompt_build": "tokenizer.json"
  },
  "levels": [
    {
      "concurrency": 1,
      "n_requests": 8,
      "n_ok": 8,
      "n_errors": 0,
      "errors": [],
      "wall_s": 167.7497703190893,
      "ttft_s": {
        "p50": 0.7368478225544095,
        "p90": 0.7410881330259145,
        "mean": 0.7100226980401203
      },
      "e2e_s": {
        "p50": 20.956795112695545,
        "p90": 22.442169491481035,
        "mean": 20.96854761627037
      },
      "decode_tok_s_per_req": {
        "p50": 12.574976715274474,
        "p90": 13.522581057360785,
        "mean": 12.629198610683233
      },
      "itl_s": {
        "p50": 0.07952795094609552,
        "p90": 0.08523689763364839,
        "mean": 0.07944462552721447
      },
      "output_tokens_mean": 256.0,
      "output_tokens_min": 256,
      "output_tokens_max": 256,
      "prompt_tokens_mean": 1051.0,
      "n_short_outputs": 0,
      "aggregate_output_tok_s": 12.208660531125302,
      "requests_per_s": 0.04769008019970821,
      "usage_reported": true
    },
    {
      "concurrency": 2,
      "n_requests": 8,
      "n_ok": 8,
      "n_errors": 0,
      "errors": [],
      "wall_s": 82.62508355267346,
      "ttft_s": {
        "p50": 0.8884775410406291,
        "p90": 1.168848348222673,
        "mean": 0.9600589442998171
      },
      "e2e_s": {
        "p50": 20.495888442732394,
        "p90": 23.237484936509283,
        "mean": 20.539230286842212
      },
      "decode_tok_s_per_req": {
        "p50": 13.113690417487145,
        "p90": 15.40404216440473,
        "mean": 13.185971019742919
      },
      "itl_s": {
        "p50": 0.07629031224687602,
        "p90": 0.08763312555082581,
        "mean": 0.0767804972402861
      },
      "output_tokens_mean": 256.0,
      "output_tokens_min": 256,
      "output_tokens_max": 256,
      "prompt_tokens_mean": 1051.0,
      "n_short_outputs": 0,
      "aggregate_output_tok_s": 24.786661773169655,
      "requests_per_s": 0.09682289755144396,
      "usage_reported": true
    },
    {
      "concurrency": 4,
      "n_requests": 8,
      "n_ok": 8,
      "n_errors": 0,
      "errors": [],
      "wall_s": 48.18132451828569,
      "ttft_s": {
        "p50": 1.4830374312587082,
        "p90": 2.075450401753187,
        "mean": 1.469463941641152
      },
      "e2e_s": {
        "p50": 22.7819732921198,
        "p90": 24.27312577702105,
        "mean": 22.48564152873587
      },
      "decode_tok_s_per_req": {
        "p50": 12.02420852876317,
        "p90": 13.446927005044758,
        "mean": 12.240232030320389
      },
      "itl_s": {
        "p50": 0.08323863003512516,
        "p90": 0.09169133495101157,
        "mean": 0.08241570999380202
      },
      "output_tokens_mean": 256.0,
      "output_tokens_min": 256,
      "output_tokens_max": 256,
      "prompt_tokens_mean": 1051.0,
      "n_short_outputs": 0,
      "aggregate_output_tok_s": 42.50609588830931,
      "requests_per_s": 0.16603943706370825,
      "usage_reported": true
    },
    {
      "concurrency": 8,
      "n_requests": 8,
      "n_ok": 8,
      "n_errors": 0,
      "errors": [],
      "wall_s": 31.786477480083704,
      "ttft_s": {
        "p50": 5.049089141655713,
        "p90": 5.0829355555586515,
        "mean": 5.062669638660736
      },
      "e2e_s": {
        "p50": 25.993340300396085,
        "p90": 29.076695342641322,
        "mean": 26.93958732835017
      },
      "decode_tok_s_per_req": {
        "p50": 12.175041260252009,
        "p90": 12.51746500245328,
        "mean": 11.74804181220008
      },
      "itl_s": {
        "p50": 0.08213639315948182,
        "p90": 0.09391973348115297,
        "mean": 0.08579115118813135
      },
      "output_tokens_mean": 256.0,
      "output_tokens_min": 256,
      "output_tokens_max": 256,
      "prompt_tokens_mean": 1051.0,
      "n_short_outputs": 0,
      "aggregate_output_tok_s": 64.42991367266805,
      "requests_per_s": 0.25167935028385957,
      "usage_reported": true
    }
  ]
}

	{
	"label": "",
	"model": "sensenova-loop-nvfp4",
	"base_url": "http://127.0.0.1:30080/v1",
	"host": "tux",
	"time": "2026-10-30T17:21:08-0700",
	"config": {
	"base_url": "http://127.0.0.1:30080/v1",
	"model": "sensenova-loop-nvfp4",
	"concurrency": "1,2,4,8",
	"num_requests": 8,
	"warmup": 2,
	"input_tokens": 1024,
	"output_tokens": 256,
	"tokenizer": "upstream/SenseNova-Loop-9B-Preview/tokenizer.json",
	"allow_prefix_cache": false,
	"no_ignore_eos": false,
	"timeout": 600,
	"label": "",
	"out": "eval/runs/perf_sglang_nvfp4_v1_mtp.json",
	"prompt_text_tokens": 1024,
	"prompt_build": "tokenizer.json"
	},
	"levels": [
	{
	"concurrency": 1,
	"n_requests": 8,
	"n_ok": 8,
	"n_errors": 0,
	"errors": [],
	"wall_s": 167.7497703190893,
	"ttft_s": {
	"p50": 0.7368478225544095,
	"p90": 0.7410881330259145,
	"mean": 0.7100226980401203
	},
	"e2e_s": {
	"p50": 20.956795112695545,
	"p90": 22.442169491481035,
	"mean": 20.96854761627037
	},
	"decode_tok_s_per_req": {
	"p50": 12.574976715274474,
	"p90": 13.522581057360785,
	"mean": 12.629198610683233
	},
	"itl_s": {
	"p50": 0.07952795094609552,
	"p90": 0.08523689763364839,
	"mean": 0.07944462552721447
	},
	"output_tokens_mean": 256.0,
	"output_tokens_min": 256,
	"output_tokens_max": 256,
	"prompt_tokens_mean": 1051.0,
	"n_short_outputs": 0,
	"aggregate_output_tok_s": 12.208660531125302,
	"requests_per_s": 0.04769008019970821,
	"usage_reported": true
	},
	{
	"concurrency": 2,
	"n_requests": 8,
	"n_ok": 8,
	"n_errors": 0,
	"errors": [],
	"wall_s": 82.62508355267346,
	"ttft_s": {
	"p50": 0.8884775410406291,
	"p90": 1.168848348222673,
	"mean": 0.9600589442998171
	},
	"e2e_s": {
	"p50": 20.495888442732394,
	"p90": 23.237484936509283,
	"mean": 20.539230286842212
	},
	"decode_tok_s_per_req": {
	"p50": 13.113690417487145,
	"p90": 15.40404216440473,
	"mean": 13.185971019742919
	},
	"itl_s": {
	"p50": 0.07629031224687602,
	"p90": 0.08763312555082581,
	"mean": 0.0767804972402861
	},
	"output_tokens_mean": 256.0,
	"output_tokens_min": 256,
	"output_tokens_max": 256,
	"prompt_tokens_mean": 1051.0,
	"n_short_outputs": 0,
	"aggregate_output_tok_s": 24.786661773169655,
	"requests_per_s": 0.09682289755144396,
	"usage_reported": true
	},
	{
	"concurrency": 4,
	"n_requests": 8,
	"n_ok": 8,
	"n_errors": 0,
	"errors": [],
	"wall_s": 48.18132451828569,
	"ttft_s": {
	"p50": 1.4830374312587082,
	"p90": 2.075450401753187,
	"mean": 1.469463941641152
	},
	"e2e_s": {
	"p50": 22.7819732921198,
	"p90": 24.27312577702105,
	"mean": 22.48564152873587
	},
	"decode_tok_s_per_req": {
	"p50": 12.02420852876317,
	"p90": 13.446927005044758,
	"mean": 12.240232030320389
	},
	"itl_s": {
	"p50": 0.08323863003512516,
	"p90": 0.09169133495101157,
	"mean": 0.08241570999380202
	},
	"output_tokens_mean": 256.0,
	"output_tokens_min": 256,
	"output_tokens_max": 256,
	"prompt_tokens_mean": 1051.0,
	"n_short_outputs": 0,
	"aggregate_output_tok_s": 42.50609588830931,
	"requests_per_s": 0.16603943706370825,
	"usage_reported": true
	},
	{
	"concurrency": 8,
	"n_requests": 8,
	"n_ok": 8,
	"n_errors": 0,
	"errors": [],
	"wall_s": 31.786477480083704,
	"ttft_s": {
	"p50": 5.049089141655713,
	"p90": 5.0829355555586515,
	"mean": 5.062669638660736
	},
	"e2e_s": {
	"p50": 25.993340300396085,
	"p90": 29.076695342641322,
	"mean": 26.93958732835017
	},
	"decode_tok_s_per_req": {
	"p50": 12.175041260252009,
	"p90": 12.51746500245328,
	"mean": 11.74804181220008
	},
	"itl_s": {
	"p50": 0.08213639315948182,
	"p90": 0.09391973348115297,
	"mean": 0.08579115118813135
	},
	"output_tokens_mean": 256.0,
	"output_tokens_min": 256,
	"output_tokens_max": 256,
	"prompt_tokens_mean": 1051.0,
	"n_short_outputs": 0,
	"aggregate_output_tok_s": 64.42991367266805,
	"requests_per_s": 0.25167935028385957,
	"usage_reported": true
	}
	]
	}