Instructions to use leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ")
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("leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ", 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 leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ",
		"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/leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ

SGLang

How to use leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ 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 "leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ" \
    --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": "leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ",
		"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 "leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ" \
        --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": "leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ",
		"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 leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ with Docker Model Runner:
```
docker model run hf.co/leoncca/Qwen3.5-122B-A10B-Heretic-Selective-AWQ
```

leoncca commited on 11 days ago

Commit

201bc91

verified ·

1 Parent(s): 17b8b6b

Show checkpoint size at top of model card

Browse files

Files changed (2) hide show

README.md +2 -0
SHA256SUMS +1 -1

README.md CHANGED Viewed

@@ -22,6 +22,8 @@ tags:
 # Qwen3.5-122B-A10B Heretic Selective AWQ
 This is an activation-aware, selectively scoped AWQ checkpoint of
 [`trohrbaugh/Qwen3.5-122B-A10B-heretic`](https://huggingface.co/trohrbaugh/Qwen3.5-122B-A10B-heretic),
 built for and runtime-validated on **4x NVIDIA Tesla V100 PCIe 32 GB (SM70)**.

 # Qwen3.5-122B-A10B Heretic Selective AWQ
+**Checkpoint size: 82.08 GB (76.45 GiB) of safetensors weights.**
 This is an activation-aware, selectively scoped AWQ checkpoint of
 [`trohrbaugh/Qwen3.5-122B-A10B-heretic`](https://huggingface.co/trohrbaugh/Qwen3.5-122B-A10B-heretic),
 built for and runtime-validated on **4x NVIDIA Tesla V100 PCIe 32 GB (SM70)**.

SHA256SUMS CHANGED Viewed

@@ -1,6 +1,6 @@
 fe81d528e7ee055bbcf6a310afe0f2808423a4a16d45225f29c285926abef08d  ./.gitattributes
 bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a  ./LICENSE
-92771e3006f5e5b48dd562cdba049310cafa0d0a584865cc12c1a18b8cd9b16c  ./README.md
 7a119e36699af82a3f6cb4f63bb9671cd42047842a1d022ed075aa11a31567d3  ./artifacts/final-output-audit.json
 96757b40c8290a819b66c6558ca7656c50ae960c106256ccb4f9dacaacb07b34  ./artifacts/gptqmodel-commit.txt
 320bc1b739acc798dca6561f4dc2b95f33b53b9d96e622c2d7f30c759bbcc6a8  ./artifacts/gptqmodel-local.patch

 fe81d528e7ee055bbcf6a310afe0f2808423a4a16d45225f29c285926abef08d  ./.gitattributes
 bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a  ./LICENSE
+8c67754c3190b04ea4f3036fabca850f8ec7b6031d8e5faa3201bc5d70626072  ./README.md
 7a119e36699af82a3f6cb4f63bb9671cd42047842a1d022ed075aa11a31567d3  ./artifacts/final-output-audit.json
 96757b40c8290a819b66c6558ca7656c50ae960c106256ccb4f9dacaacb07b34  ./artifacts/gptqmodel-commit.txt
 320bc1b739acc798dca6561f4dc2b95f33b53b9d96e622c2d7f30c759bbcc6a8  ./artifacts/gptqmodel-local.patch