Instructions to use Chungulus/Qwen3.8-27B-GPTQ-INT4-G32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use Chungulus/Qwen3.8-27B-GPTQ-INT4-G32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Chungulus/Qwen3.8-27B-GPTQ-INT4-G32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chungulus/Qwen3.8-27B-GPTQ-INT4-G32",
		"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/Chungulus/Qwen3.8-27B-GPTQ-INT4-G32

SGLang

How to use Chungulus/Qwen3.8-27B-GPTQ-INT4-G32 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 "Chungulus/Qwen3.8-27B-GPTQ-INT4-G32" \
    --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": "Chungulus/Qwen3.8-27B-GPTQ-INT4-G32",
		"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 "Chungulus/Qwen3.8-27B-GPTQ-INT4-G32" \
        --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": "Chungulus/Qwen3.8-27B-GPTQ-INT4-G32",
		"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 Chungulus/Qwen3.8-27B-GPTQ-INT4-G32 with Docker Model Runner:
```
docker model run hf.co/Chungulus/Qwen3.8-27B-GPTQ-INT4-G32
```

Qwen3.8-27B-GPTQ-INT4-G32 / build_provenance.json

Chungulus

Upload validated GPTQ-INT4-G32 quantization

958c7e6 verified 10 days ago

Raw

History Blame Contribute Delete

2 kB

	{
	"target": "GPTQ-INT4-G32",
	"status": "complete",
	"smoke_test": false,
	"started_utc": "2026-08-16T10:21:50+00:00",
	"source": "/mnt/c/Users/chunk/OneDrive/Documents/quant3.8/qwen38-cuda-quants/hf-cache/source/Qwen3.8-27B--1d4bf0f2ff60",
	"pinned_source_revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
	"output": "/mnt/c/Users/chunk/OneDrive/Documents/quant3.8/qwen38-cuda-quants/outputs/Qwen3.8-27B-GPTQ-INT4-G32",
	"configuration": {
	"bits": 4,
	"group_size": 32,
	"desc_act": true,
	"lm_head": false,
	"method": "gptq",
	"quant_method": "gptq",
	"format": "gptq",
	"checkpoint_format": "gptq",
	"pack_dtype": "int32",
	"meta": {
	"fallback": {
	"strategy": "rtn",
	"threshold": "0.5%",
	"smooth": null
	},
	"offload_to_disk": false,
	"offload_to_disk_path": null,
	"pack_impl": "cpu",
	"gc_mode": "interval",
	"wait_for_submodule_finalizers": false,
	"auto_forward_data_parallel": true,
	"dense_vram_strategy": "exclusive",
	"dense_vram_strategy_devices": null,
	"moe_vram_strategy": "exclusive",
	"moe_vram_strategy_devices": null,
	"gptaq": null,
	"mse": 0.0,
	"mock_quantization": false,
	"act_group_aware": false,
	"hessian": {
	"chunk_size": null,
	"chunk_bytes": null,
	"staging_dtype": "float32"
	}
	},
	"sym": true,
	"calibration_samples": 128,
	"calibration_sequence_length": 2048,
	"calibration_batch_size": 1,
	"calibration_sort": true,
	"calibration_corpus_sha256": "7ac4e3f0092bd5acfdeaec88f19a8c829458b0716c10ab9e81cda6f8b064b675",
	"estimated_output_bytes_for_disk_gate": 25013756783
	},
	"gptqmodel_quantized": true,
	"finished_utc": "2026-08-16T11:25:21+00:00",
	"elapsed_seconds": 3874.993,
	"resources": {
	"samples": 3652,
	"peak_process_rss_gib": 30.644,
	"peak_system_used_gib": 19.263,
	"peak_gpu_vram_gib": 10.301
	},
	"output_bytes": 21008177453
	}