Instructions to use SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-FP8")
model = AutoModelForMultimodalLM.from_pretrained("SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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": "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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/SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-FP8

SGLang

How to use SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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 "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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": "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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 "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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": "SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-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 SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-FP8 with Docker Model Runner:
```
docker model run hf.co/SwissNeuron/Qwen3.8-27B-SwissNeuron-Derisked-FP8
```

Swiss-guy commited on 2 days ago

Commit

db91044

verified ·

1 Parent(s): a8d2308

Register restored MTP tensors

Browse files

Files changed (1) hide show

model.safetensors.index.json +17 -2

model.safetensors.index.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "metadata": {
     "total_parameters": 27360632560,
-    "total_size": 30370708960
   },
   "weight_map": {
     "lm_head.weight": "model-00001-of-00007.safetensors",
@@ -1683,6 +1683,21 @@
     "model.visual.merger.norm.weight": "model-00007-of-00007.safetensors",
     "model.visual.patch_embed.proj.bias": "model-00007-of-00007.safetensors",
     "model.visual.patch_embed.proj.weight": "model-00007-of-00007.safetensors",
-    "model.visual.pos_embed.weight": "model-00007-of-00007.safetensors"
   }
 }

 {
   "metadata": {
     "total_parameters": 27360632560,
+    "total_size": 31220322464
   },
   "weight_map": {
     "lm_head.weight": "model-00001-of-00007.safetensors",
     "model.visual.merger.norm.weight": "model-00007-of-00007.safetensors",
     "model.visual.patch_embed.proj.bias": "model-00007-of-00007.safetensors",
     "model.visual.patch_embed.proj.weight": "model-00007-of-00007.safetensors",
+    "model.visual.pos_embed.weight": "model-00007-of-00007.safetensors",
+    "mtp.fc.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.input_layernorm.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.mlp.down_proj.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.mlp.gate_proj.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.mlp.up_proj.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.post_attention_layernorm.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.self_attn.k_norm.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.self_attn.k_proj.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.self_attn.o_proj.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.self_attn.q_norm.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.self_attn.q_proj.weight": "model-mtp-bf16.safetensors",
+    "mtp.layers.0.self_attn.v_proj.weight": "model-mtp-bf16.safetensors",
+    "mtp.norm.weight": "model-mtp-bf16.safetensors",
+    "mtp.pre_fc_norm_embedding.weight": "model-mtp-bf16.safetensors",
+    "mtp.pre_fc_norm_hidden.weight": "model-mtp-bf16.safetensors"
   }
 }