Instructions to use Mantisec/Qwen3.5-4B-FP16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mantisec/Qwen3.5-4B-FP16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Mantisec/Qwen3.5-4B-FP16")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Mantisec/Qwen3.5-4B-FP16")
model = AutoModelForMultimodalLM.from_pretrained("Mantisec/Qwen3.5-4B-FP16", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mantisec/Qwen3.5-4B-FP16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mantisec/Qwen3.5-4B-FP16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mantisec/Qwen3.5-4B-FP16",
		"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/Mantisec/Qwen3.5-4B-FP16

SGLang

How to use Mantisec/Qwen3.5-4B-FP16 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 "Mantisec/Qwen3.5-4B-FP16" \
    --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": "Mantisec/Qwen3.5-4B-FP16",
		"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 "Mantisec/Qwen3.5-4B-FP16" \
        --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": "Mantisec/Qwen3.5-4B-FP16",
		"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 Mantisec/Qwen3.5-4B-FP16 with Docker Model Runner:
```
docker model run hf.co/Mantisec/Qwen3.5-4B-FP16
```

Qwen3.5-4B-fp16

FP16 conversion of Qwen/Qwen3.5-4B, produced by bfsquish v0.1.0.

Intended use

Optimized for FP16 inference and fine-tuning on NVIDIA V100 (Volta) GPUs, which lack native BF16 Tensor Core support. The weights have been converted from BF16 to FP16 using the effective clamp_only strategy (see below).

Conversion details

Field	Value
Source model	`Qwen/Qwen3.5-4B`
Source revision	`latest`
Requested strategy	`auto`
Effective strategy	`clamp_only`
Tool	`bfsquish` v0.1.0
Converted at (UTC)	`2026-09-05T13:51:06.034581+00:00`
Target hardware	NVIDIA V100 (Volta, sm_70)
Target runtime	NVIDIA V100 (Volta sm_70), FP16 Tensor Cores

Conversion strategy

Direct upcast to FP32, clamp to FP16 range (+/-65504), downcast to FP16. The simplest strategy, near-lossless for well-behaved trained weights whose values are concentrated near zero.

Transform plan

v1 strategy applied: clamp_only (no v2 plan bundle was produced for this conversion).

Enhanced chat template

Prompt rendering uses the selected third-party enhanced template; model weights are unchanged by this step. The standalone and embedded forms were smoke-rendered to the same prompt before publication.

Field	Value
Selection	`latest`
Source	`peculiar-ragdoll/Qwen-Sharp-Chat-Templates`
Resolved revision	`fa3a1295882d31132770c156fced4e616b5db25d`
Template version	`qwen3.8-froggeric-v22.4.0`
Template license	`Apache-2.0`
Published forms	`chat_template.jinja` and `tokenizer_config.json#chat_template`

Reproduce the prompt-format step with --chat-template latest --chat-template-repo peculiar-ragdoll/Qwen-Sharp-Chat-Templates --chat-template-revision fa3a1295882d31132770c156fced4e616b5db25d.

Numerical quality

Metric	Value
Validation verdict	PASS
Validation method	`generate`
Max abs logit diff (vs. source)	0.215126
Min cosine similarity (vs. source)	0.999978
Token agreement rate	100.00%
Inf/NaN scan	passed (no inf/nan)

Validation notes

generation agreement passed despite logit drift: token_agreement=100.00% (pass≥98.00%), min_cos=0.999978, max_diff=0.2151

Reproducing this conversion

bfsquish run \
  --model Qwen/Qwen3.5-4B \
  --output-dir ./out \
  --strategy auto

License

Inherited from the source model. Refer to the source model's license for terms of use.

Downloads last month: 30

Safetensors

Model size

5B params

Tensor type

F16

Model tree for Mantisec/Qwen3.5-4B-FP16

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(639)

this model