Instructions to use CuTIsolation/Qwen3.8-27B-W4A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CuTIsolation/Qwen3.8-27B-W4A8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="CuTIsolation/Qwen3.8-27B-W4A8")
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("CuTIsolation/Qwen3.8-27B-W4A8")
model = AutoModelForMultimodalLM.from_pretrained("CuTIsolation/Qwen3.8-27B-W4A8", 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 CuTIsolation/Qwen3.8-27B-W4A8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CuTIsolation/Qwen3.8-27B-W4A8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CuTIsolation/Qwen3.8-27B-W4A8",
		"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/CuTIsolation/Qwen3.8-27B-W4A8

SGLang

How to use CuTIsolation/Qwen3.8-27B-W4A8 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 "CuTIsolation/Qwen3.8-27B-W4A8" \
    --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": "CuTIsolation/Qwen3.8-27B-W4A8",
		"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 "CuTIsolation/Qwen3.8-27B-W4A8" \
        --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": "CuTIsolation/Qwen3.8-27B-W4A8",
		"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 CuTIsolation/Qwen3.8-27B-W4A8 with Docker Model Runner:
```
docker model run hf.co/CuTIsolation/Qwen3.8-27B-W4A8
```

Qwen3.8-27B W4A8 (for ComfyUI)

W4A8 quantized version of Qwen3.5/Qwen3.8-27B (qwen3_5 architecture) as a single safetensors file, loadable directly by ComfyUI. Weights are compressed from 27.9GB (BF16) to 16.7GB.

Model Overview

Base model: Qwen3.8-27B (Apache-2.0)
Quantization format: asym_w4a8_int8 (4-bit weights, int8 activations)
Grouping: weight group_size = 16, convrot_groupsize = 256
Quantization algorithm: comfy-kitchen AsymW4A8Int8Layout
- ConvRot Hadamard rotation (256-blocks) followed by per-group quantization
- Per-group 16-level Lloyd-Max codebook + fp8 group scales + fp32 channel scales
File size: qwen3.8-27b-w4a8.safetensors ≈ 16.7GB

Conversion Scope

Action	Layers
Quantized (int4)	LM linear projections: in_proj_qkv/z/b/a, out_proj, q/k/v/o_proj, gate/up/down_proj, lm_head
Kept BF16	Vision tower, embeddings, norms, DeltaNet conv1d
Dropped	MTP head (not supported by ComfyUI's Qwen35 implementation)

ComfyUI Usage

Put qwen3.8-27b-w4a8.safetensors into ComfyUI/models/text_encoders/.
Select the file in a CLIP Loader. ComfyUI auto-detects it as QWEN35_27B (detect_te_model) and enables mixed-precision layers (llama_detect → llama_quantization_metadata).
Quantized layers run through the AsymW4A8Int8Layout CUDA/Triton kernels.

Accuracy

Dequantizing a single layer (in_proj_qkv) reproduces comfy-kitchen's quantization of the original BF16 weight bit-for-bit (relative error 0.00000, checks passed).
Typical W4A8 forward error vs full-precision BF16 is ~1% (varies by layer and data distribution).
It is recommended to run your own quality evaluation before deploying.

Hardware Requirements

NVIDIA GPU (Ampere or newer, CUDA 13.0+) recommended for the optimized comfy-kitchen CUDA backend; CPU / Triton fall back gracefully.
Conversion measured on RTX 4060 (8GB VRAM) from 52GB BF16 shards: ~4 minutes.

Conversion Tool

Quantized with convert_qwen35_w4a8.py (comfy-kitchen quantization backend), shipped alongside the ComfyUI repo:

python convert_qwen35_w4a8.py \
    --input-dir ./qwen38_27b \
    --output ./qwen3.8-27b-w4a8.safetensors \
    --verify

License & Disclaimer

The base model is Apache-2.0; this quantized model is released under the same license. This is a community quantization and differs from the original weights in accuracy. Use at your own discretion; please comply with the base model's terms of use and applicable laws in your jurisdiction.

Downloads last month: 154

Model tree for CuTIsolation/Qwen3.8-27B-W4A8

Base model

Qwen/Qwen3.8-27B

Finetuned

(154)

this model