Instructions to use rzgar/Qwen3.8-27B-NVFP4-ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rzgar/Qwen3.8-27B-NVFP4-ComfyUI with Transformers:

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

pipe = pipeline("image-text-to-text", model="rzgar/Qwen3.8-27B-NVFP4-ComfyUI")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("rzgar/Qwen3.8-27B-NVFP4-ComfyUI")
model = AutoModelForMultimodalLM.from_pretrained("rzgar/Qwen3.8-27B-NVFP4-ComfyUI", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rzgar/Qwen3.8-27B-NVFP4-ComfyUI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rzgar/Qwen3.8-27B-NVFP4-ComfyUI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rzgar/Qwen3.8-27B-NVFP4-ComfyUI",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rzgar/Qwen3.8-27B-NVFP4-ComfyUI

SGLang

How to use rzgar/Qwen3.8-27B-NVFP4-ComfyUI 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 "rzgar/Qwen3.8-27B-NVFP4-ComfyUI" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rzgar/Qwen3.8-27B-NVFP4-ComfyUI",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "rzgar/Qwen3.8-27B-NVFP4-ComfyUI" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rzgar/Qwen3.8-27B-NVFP4-ComfyUI",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rzgar/Qwen3.8-27B-NVFP4-ComfyUI with Docker Model Runner:
```
docker model run hf.co/rzgar/Qwen3.8-27B-NVFP4-ComfyUI
```

Qwen3.8-27B ComfyUI NVFP4

A ComfyUI-native quantized conversion of unsloth/Qwen3.8-27B-NVFP4

Unlike the core node, the custom node doesn’t run for max_length steps and finishes within seconds

File

File	Download
`Qwen3.8-27B-nvfp4-comfy.safetensors`	Download 22.6 GB
`Qwen3.8-27B-nvfp4-all-comfy.safetensors`	Download 16GB

Usage

Place the file in ComfyUI/models/text_encoders/ and load it with the LLM/text-encoder loader. Use with the Generate Text node.

Recommended: the "Generate Text (Qwen3.8)" custom node (install ComfyUI-Qwen3.8-Text)

The official Generate Text node for quantized checkpoints, it projects the output through

the embedding table instead of the real lm_head (untied), which produces incoherent text that never stops and runs to max_length.

The custom node formats the prompt with the model's own chat template, uses the correct lm_head weights, and supports image and video inputs typical captions/answers finish in seconds.

Comparison

	`...-nvfp4-all-comfy`	`...-nvfp4-comfy`
Size	16 GB	22.6 GB
MLP	NVFP4 (fp4)	NVFP4 (fp4)
Attention / linear-attn / lm_head	NVFP4 (fp4)	FP8 (e4m3)
Embeddings	FP8 (per-tensor)	BF16
Vision tower	NVFP4	BF16
Quality	slightly lower attention precision	fp8 attention, mirrors unsloth's design

Downloads last month: -

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rzgar/Qwen3.8-27B-NVFP4-ComfyUI

Base model

Qwen/Qwen3.8-27B

Quantized

(300)

this model