Instructions to use writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw with Transformers:

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

pipe = pipeline("image-text-to-text", model="writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw")
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("writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw")
model = AutoModelForMultimodalLM.from_pretrained("writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw", 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 writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw",
		"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/writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw

SGLang

How to use writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw 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 "writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw" \
    --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": "writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw",
		"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 "writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw" \
        --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": "writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw",
		"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 writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw with Docker Model Runner:
```
docker model run hf.co/writetoasik/Qwen3.8-27B-Uncensored-exl3-4.0bpw
```

writetoasik commited on 9 days ago

Commit

0189717

verified ·

1 Parent(s): 9d821cd

Note Hub param-count widget is packed EXL3, not 8B

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -43,7 +43,7 @@ This is a **weight-only re-quant**, not a new train. The vision tower and MTP sp
 | **Architecture** | `Qwen3_5ForConditionalGeneration` — 64 layers, hidden 5120, hybrid Gated DeltaNet (48 linear + 16 full attention) |
 | **Load with** | ExLlamaV3 ≥ 1.4.3 or [TabbyAPI](https://github.com/theroyallab/tabbyAPI) (official ExLlama V3 server) |
-Not a GGUF, not FP8, not for `transformers` `generate()` / vLLM / llama.cpp.
 Sibling quants of the same uncensored source: [FP8](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-FP8) · [GGUF](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-GGUF) · [MLX](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-MLX). Official (censored) EXL3 of the base: [`turboderp/Qwen3.8-27B-exl3`](https://huggingface.co/turboderp/Qwen3.8-27B-exl3).

 | **Architecture** | `Qwen3_5ForConditionalGeneration` — 64 layers, hidden 5120, hybrid Gated DeltaNet (48 linear + 16 full attention) |
 | **Load with** | ExLlamaV3 ≥ 1.4.3 or [TabbyAPI](https://github.com/theroyallab/tabbyAPI) (official ExLlama V3 server) |
+Not a GGUF, not FP8, not for `transformers` `generate()` / vLLM / llama.cpp. The Hub “model size” widget under-counts (packed EXL3 tensors look like ~8B); this is the full **27B**.
 Sibling quants of the same uncensored source: [FP8](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-FP8) · [GGUF](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-GGUF) · [MLX](https://huggingface.co/orcarouter/Qwen3.8-27B-Uncensored-MLX). Official (censored) EXL3 of the base: [`turboderp/Qwen3.8-27B-exl3`](https://huggingface.co/turboderp/Qwen3.8-27B-exl3).