Instructions to use ProCreations/nib-4b-preview-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ProCreations/nib-4b-preview-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ProCreations/nib-4b-preview-FP8")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ProCreations/nib-4b-preview-FP8")
model = AutoModelForMultimodalLM.from_pretrained("ProCreations/nib-4b-preview-FP8", 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 ProCreations/nib-4b-preview-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ProCreations/nib-4b-preview-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ProCreations/nib-4b-preview-FP8",
		"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/ProCreations/nib-4b-preview-FP8

SGLang

How to use ProCreations/nib-4b-preview-FP8 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 "ProCreations/nib-4b-preview-FP8" \
    --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": "ProCreations/nib-4b-preview-FP8",
		"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 "ProCreations/nib-4b-preview-FP8" \
        --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": "ProCreations/nib-4b-preview-FP8",
		"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 ProCreations/nib-4b-preview-FP8 with Docker Model Runner:
```
docker model run hf.co/ProCreations/nib-4b-preview-FP8
```

Nib 4B (preview), FP8

FP8 weights of Nib 4B, in the same 128×128 block layout as Qwen's official FP8 releases (e4m3 weights, BF16 block scales, dynamic activations), with clipping calibrated on in-domain agent episodes including screenshots. 5.8 GB.

Only the main linear projections are quantized. The vision encoder, embeddings and tied output head, all norms, the Gated DeltaNet gates, convolutions and decay parameters, and the MTP weights are kept byte-for-byte from the BF16 model (in nib-protected.safetensors).

	Mean KL vs BF16	p99 KL	Top-1 agreement	Browser tasks (581-task live set, paired)
FP8	0.0028	0.033	98.9%	42.5% vs 45.3% for BF16 (−2.8, 95% CI −6.4 to +1.0)

Fidelity is measured against the BF16 model on 5,070 held-out assistant tokens from 48 complete agent episodes (up to 32k tokens, ten harnesses), none used for calibration. The functional difference is within run-to-run noise: the NVFP4 build, with 5× this KL, scored 45.6% on the same tasks.

Serving (tested: SGLang 0.5.21)

python -m sglang.launch_server \
  --model-path ProCreations/nib-4b-preview-FP8 --served-model-name nib-4b \
  --context-length 131072 --reasoning-parser qwen3 --tool-call-parser qwen3_coder \
  --mamba-ssm-dtype bfloat16 --mamba-radix-cache-strategy extra_buffer_lazy --trust-remote-code

Tested on an RTX PRO 6000 (Blackwell) with CUDA graphs, radix cache and 8 concurrent requests.

Reasoning effort

Same as Nib 4B: pass chat_template_kwargs {"enable_thinking": false} for thinking off, or {"enable_thinking": true, "reasoning_effort": "low" | "medium" | "xhigh"} (xhigh is the default). All our evaluations used temperature 1.0 and top_p 0.95.

About Nib

Nib is Qwen3.5-4B post-trained as a browser agent across common agent harnesses. Benchmarks, usage, training details and limitations (including that it often reports success on tasks it did not finish) are on the main model card. This is a preview release.

License: Apache 2.0, the same as the base model Qwen/Qwen3.5-4B.

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

F8_E4M3

F32

BF16

Model tree for ProCreations/nib-4b-preview-FP8

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

ProCreations/nib-4b-preview

Quantized

(3)

this model