Instructions to use f3nc3r/Qwable-9B-Claude-Fable-5-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use f3nc3r/Qwable-9B-Claude-Fable-5-NPU2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="f3nc3r/Qwable-9B-Claude-Fable-5-NPU2")
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("f3nc3r/Qwable-9B-Claude-Fable-5-NPU2")
model = AutoModelForMultimodalLM.from_pretrained("f3nc3r/Qwable-9B-Claude-Fable-5-NPU2", 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 f3nc3r/Qwable-9B-Claude-Fable-5-NPU2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "f3nc3r/Qwable-9B-Claude-Fable-5-NPU2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "f3nc3r/Qwable-9B-Claude-Fable-5-NPU2",
		"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/f3nc3r/Qwable-9B-Claude-Fable-5-NPU2

SGLang

How to use f3nc3r/Qwable-9B-Claude-Fable-5-NPU2 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 "f3nc3r/Qwable-9B-Claude-Fable-5-NPU2" \
    --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": "f3nc3r/Qwable-9B-Claude-Fable-5-NPU2",
		"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 "f3nc3r/Qwable-9B-Claude-Fable-5-NPU2" \
        --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": "f3nc3r/Qwable-9B-Claude-Fable-5-NPU2",
		"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 f3nc3r/Qwable-9B-Claude-Fable-5-NPU2 with Docker Model Runner:
```
docker model run hf.co/f3nc3r/Qwable-9B-Claude-Fable-5-NPU2
```

f3nc3r commited on 17 days ago

Commit

26fa89b

verified ·

1 Parent(s): c9986c9

Add quantization tag and clarify Q4NX quantized model conversion

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -7,21 +7,21 @@ tags:
 - fastflowlm
 - npu
 - npu2
-- q4nx
 - amd-xdna
 - lemonade
 ---
-# Qwable-9B-Claude-Fable-5-NPU2 (FastFlowLM / Lemonade NPU2)
 > [!IMPORTANT]
-> **FLM v1.0.3+ Runtime Compatibility Note:**
-> This model has been specifically **re-quantized** to run on **FastFlowLM (`flm`) v1.0.3+** and **Lemonade** on AMD XDNA NPU hardware.
 >
 > * **Details**: Re-quantized to Q4NX format for FastFlowLM v1.0.3+ and Lemonade on AMD XDNA NPU. Fine-tuned for agentic coding and reasoning, configured with full EOS stop token sequence IDs ([248044, 248046]).
-> * **Architecture**: Qwable 9B (Qwen3.5 9B base fine-tune)
-> * **Quantization**: Q4_K / Q4_1 / Q8_0 hybrid Q4NX
-> * **Source Model**: [empero-ai/Qwable-9B-Claude-Fable-5](https://huggingface.co/empero-ai/Qwable-9B-Claude-Fable-5)
 > * **Format**: `Q4NX` (safetensors format with AMD NPU block packing). Note that this is **not** a standard GGUF file; it is executed natively via `flm` / Lemonade on AMD Ryzen AI NPUs.
 ---

 - fastflowlm
 - npu
 - npu2
 - amd-xdna
 - lemonade
 ---
+# Qwable-9B-Claude-Fable-5-NPU2 (FastFlowLM / Lemonade NPU2 Quantization)
 > [!IMPORTANT]
+> **Quantization & NPU Compatibility Note:**
+> This repository contains **Q4NX quantized weights** converted from [empero-ai/Qwable-9B-Claude-Fable-5](https://huggingface.co/empero-ai/Qwable-9B-Claude-Fable-5) to run natively on **FastFlowLM (`flm`) v1.0.3+** and **Lemonade** on AMD XDNA NPU hardware.
 >
+> * **Model Type**: Quantized model conversion (NPU Q4NX format)
+> * **Parent / Base Model**: [empero-ai/Qwable-9B-Claude-Fable-5](https://huggingface.co/empero-ai/Qwable-9B-Claude-Fable-5)
 > * **Details**: Re-quantized to Q4NX format for FastFlowLM v1.0.3+ and Lemonade on AMD XDNA NPU. Fine-tuned for agentic coding and reasoning, configured with full EOS stop token sequence IDs ([248044, 248046]).
+> * **Architecture**: Qwable 9B (Qwen3.5 9B architecture)
+> * **Quantization Format**: Q4_K / Q4_1 / Q8_0 hybrid Q4NX
 > * **Format**: `Q4NX` (safetensors format with AMD NPU block packing). Note that this is **not** a standard GGUF file; it is executed natively via `flm` / Lemonade on AMD Ryzen AI NPUs.
 ---