Text encoder
qwen_3_ 4b_ fp8_ mixed. safetensors
Qwen 3 4b FP8 mixed · Text encoder for ComfyUI
- File
qwen_3_4b_fp8_mixed.safetensors- Type
- Text encoder
- Size
- 5.63 GB
- Folder
ComfyUI/models/text_encoders/- Source
- Comfy-Org/Z-Image-Turbo
- SHA-256
72450b197581…
1 workflow uses this file
What is Qwen 3 4b FP8 mixed?
Qwen 3 4b FP8 mixed is a text encoder that converts prompts into embeddings used to guide generation. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Qwen 3 4b FP8 mixed with other models and custom nodes to build any pipeline you need. There is 1 official ComfyUI workflow template that uses Qwen 3 4b FP8 mixed, ready to load and customize.
Workflows for this file
- Z-Image-Turbo
Z-Image-Turbo Text to Image
- Z-Image-Turbo
Z-Image-Turbo Fun Union ControlNet
- Z-Image-Turbo
Image Upscale: Z-Image-Turbo 2K
- Z-Image-Turbo, SDXL
Skin Enhancer + Upscaler
- Z-Image-Turbo
Prompt Multi Batch Generation
- Z-Image-Turbo
Batch Process Text Prompts From List
- Z-Image-Turbo
Switch Node
- Flux, Flux.2 Dev
Flux.2 Dev: Image Edit
Frequently Asked Questions
Qwen 3 4b FP8 mixed is a text encoder that converts prompts into embeddings used to guide generation. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Qwen 3 4b FP8 mixed with other models and custom nodes to build any pipeline you need. There is 1 official ComfyUI workflow template that uses Qwen 3 4b FP8 mixed, ready to load and customize.
Open ComfyUI and browse the official ComfyUI workflow template that uses Qwen 3 4b FP8 mixed. Load one as a starting point, then customize the nodes and parameters to fit your use case.
There is 1 official ComfyUI workflow template that uses Qwen 3 4b FP8 mixed. It is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Qwen 3 4b FP8 mixed weights are available to download from Hugging Face. You only pay for compute when running on Comfy Cloud; local inference on your own hardware is always free.