Instructions to use switzerchees/Reasoning-Medical-27B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use switzerchees/Reasoning-Medical-27B-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="switzerchees/Reasoning-Medical-27B-NVFP4")
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("switzerchees/Reasoning-Medical-27B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("switzerchees/Reasoning-Medical-27B-NVFP4")
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 switzerchees/Reasoning-Medical-27B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "switzerchees/Reasoning-Medical-27B-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": "switzerchees/Reasoning-Medical-27B-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/switzerchees/Reasoning-Medical-27B-NVFP4

SGLang

How to use switzerchees/Reasoning-Medical-27B-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 "switzerchees/Reasoning-Medical-27B-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": "switzerchees/Reasoning-Medical-27B-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 "switzerchees/Reasoning-Medical-27B-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": "switzerchees/Reasoning-Medical-27B-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 switzerchees/Reasoning-Medical-27B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/switzerchees/Reasoning-Medical-27B-NVFP4
```

Reasoning-Medical-27B-NVFP4

Blackwell-oriented ModelOpt quantization of EpistemeAI/Reasoning-Medical-27B, pinned to revision e5cfbcc2498df44c07124f670a75c77179fc8e67. The exported safetensors total 21.92 GB.

Quantization

NVIDIA Model Optimizer: 0.45.0
Recipe: huggingface/qwen3_5/ptq/w4a16_nvfp4-fp8_attn-kv_fp8_cast
MLP projections and lm_head: W4A16 NVFP4
Self-attention and the large linear-attention projections: FP8
KV cache metadata: FP8 cast
Preserved at source precision: vision tower, MTP, convolution and sensitive Gated-DeltaNet projections selected by the NVIDIA recipe
Calibration: 512 CNN/DailyMail text samples of at most 512 tokens; medical benchmark cases were not used
Source license: Apache-2.0

Full provenance and SHA-256 hashes are in quantization_manifest.json.

vLLM

vllm serve switzerchees/Reasoning-Medical-27B-NVFP4 \
  --served-model-name EpistemeAI/Reasoning-Medical-27B \
  --quantization modelopt \
  --kv-cache-dtype bfloat16 \
  --max-model-len 32768 \
  --reasoning-parser qwen3 \
  --limit-mm-per-prompt '{"image": 1, "video": 0}'

BF16 KV cache is recommended for accuracy and is forced explicitly above. The exported recipe contains FP8 KV-cache metadata; with vLLM 0.23, leaving the flag at auto therefore selects FP8 rather than the model's BF16 dtype. FP8 KV serving should be treated as a separate accuracy/performance trade-off and validated for the target runtime.

Limitations and safety

This quantized derivative has not been clinically validated. The upstream model card reports medical benchmarks but no independent clinical validation and no substantive medical-image benchmark. Quantization can introduce additional errors. Do not use this model as a substitute for a physician, for autonomous diagnosis, or for treatment decisions. German-language quality is evaluated separately and is not implied by the upstream model's English language tag.

Downloads last month: -

Safetensors

Model size

18B params

Tensor type

BF16

F8_E4M3

Model tree for switzerchees/Reasoning-Medical-27B-NVFP4

Base model

Qwen/Qwen3.6-27B

Finetuned

unsloth/Qwen3.6-27B

Finetuned

EpistemeAI/Reasoning-Medical-27B

Quantized

(3)

this model