Instructions to use deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit")
model = AutoModelForMultimodalLM.from_pretrained("deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit",
		"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/deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit

SGLang

How to use deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit 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 "deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit" \
    --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": "deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit",
		"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 "deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit" \
        --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": "deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit",
		"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 deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit with Docker Model Runner:
```
docker model run hf.co/deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit
```

Qwopus3.8-27B-Flash GPTQ 4-bit (FOEM)

GPTQ 4-bit quantization of Jackrong/Qwopus3.8-27B-Flash using the FOEM (First-Order Error Matters) recipe, quantized with gptqmodel and validated end-to-end on vLLM (TP2, 262K context).

Attribution & Credits

This is a quantized derivative. All credit for the underlying model belongs to its original developers:

Contribution	Developer	Model / Link
Original base model	Qwen Team (Alibaba)	`Qwen/Qwen3.8-27B`
Fine-tune ("Flash" reasoning-stability training)	Jackrong	`Jackrong/Qwopus3.8-27B-Flash`
Quantization method (FOEM + GPTQ)	ModelCloud (GPTQModel) / FOEM authors	GPTQModel · FOEM (AAAI 2026)
Quantization performed by	deluxetiky (Sinan)	this repo

License: Apache-2.0 (inherited from the base and fine-tune).

Quantization Details

Method: GPTQ 4-bit with FOEM error compensation (FOEM + GPTAQ hybrid)
Group size: 32 (g32)
Symmetric: yes · desc_act: false · lm_head: not quantized
mse: 2.0 · damp_percent: 0.05 · true_sequential: yes
FOEM: α=0.25, β=0.2 · act_group_aware: yes
Tool: gptqmodel (FOEMConfig), calibration: C4 (128 samples)
Format: gptq, int32-packed → vLLM Marlin/GPTQ kernel path

This reproduces the exact recipe used for the production btbtyler09/Qwen3.8-27B-GPTQ-4bit checkpoint so results are comparable.

Serving

Tested on vLLM 0.27.1 with the GDN FlashInfer decode backport, 2× RTX 5090 (TP2):

vllm serve deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit \
  --tensor-parallel-size 2 --max-model-len 262144 --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.92 --reasoning-parser qwen3 \
  --gdn-decode-backend flashinfer --mamba-block-size 16 --enable-prefix-caching \
  --enable-auto-tool-choice --tool-call-parser qwen3_xml

Measured A/B vs base (same quant, same stack)

Head-to-head against the stock Qwen3.8-27B (same FOEM g32 quant) on 2×5090 TP2:

Metric	Qwen3.8 base	Qwopus-Flash	Gain
Decode @1 stream	~61 tok/s	~99 tok/s	+64%
Aggregate @8 concurrent	~232 tok/s	~600 tok/s	+159%
Long task completion (6-task planner suite, 3000-tok cap)	4/6 answered; 2 truncated empty	4/6 answered incl. 7.8k-char outputs; 2 truncated	completes far more
Code correctness (execution-graded, 6 tasks / 29 tests)	24/29 (83%)	24/29 (83%)	tie

Note: this A/B ran on two different physical 2×5090 boxes (same GPU/stack), so absolute concurrency figures should be re-validated on identical hardware; the completion-rate difference is cap-bound and box-independent.

Files

6 × model-*.safetensors (~20 GB total) + config, tokenizer, chat template.

Downloads last month: 28

Safetensors

Model size

28B params

Tensor type

BF16

I32

Model tree for deluxetiky/Qwopus3.8-27B-Flash-GPTQ-4bit

Base model

Qwen/Qwen3.8-27B

Finetuned

Jackrong/Qwopus3.8-27B-Flash

Quantized

(36)

this model