Instructions to use nameistoken/Step-3.7-Flash-Quark-W8A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nameistoken/Step-3.7-Flash-Quark-W8A8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="nameistoken/Step-3.7-Flash-Quark-W8A8", 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)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nameistoken/Step-3.7-Flash-Quark-W8A8", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nameistoken/Step-3.7-Flash-Quark-W8A8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nameistoken/Step-3.7-Flash-Quark-W8A8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nameistoken/Step-3.7-Flash-Quark-W8A8",
		"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/nameistoken/Step-3.7-Flash-Quark-W8A8

SGLang

How to use nameistoken/Step-3.7-Flash-Quark-W8A8 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 "nameistoken/Step-3.7-Flash-Quark-W8A8" \
    --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": "nameistoken/Step-3.7-Flash-Quark-W8A8",
		"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 "nameistoken/Step-3.7-Flash-Quark-W8A8" \
        --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": "nameistoken/Step-3.7-Flash-Quark-W8A8",
		"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 nameistoken/Step-3.7-Flash-Quark-W8A8 with Docker Model Runner:
```
docker model run hf.co/nameistoken/Step-3.7-Flash-Quark-W8A8
```

Step-3.7-Flash W8A8 (AMD Quark → compressed-tensors)

Symmetric INT8 weights (per-channel) with INT8 dynamic per-token activations.

Base model: Step-3.7-Flash (multimodal Step3p7ForConditionalGeneration, 196B total / A11B sparse MoE, 288 routed experts top-8)
Quantization tool: AMD Quark 0.11.2 (int8, file2file), then losslessly repacked to the compressed-tensors format so that vLLM can load it.
Calibration: weight-only PTQ (RTN), no activation calibration. Activations are quantized dynamically per-token at inference time (no calibration needed).
Excluded from quantization: lm_head, MoE router (moe.gate, router_bias), share_expert, self_attn.g_proj, dense layers 0-2, MTP layers 45-47, and the full vision tower.

Usage (vLLM)

vllm serve <this-repo> --trust-remote-code --tensor-parallel-size 2 --enable-expert-parallel

NOTE: vLLM gates INT8 MoE behind current_platform.is_cuda(), which excludes ROCm. The Triton INT8 MoE kernel actually runs fine on MI355X; patch fused_moe/experts/triton_moe.py to force device_supports_int8 = True before launching.

Downloads last month: 23

Safetensors

Model size

201B params

Tensor type

BF16

F32