--- title: "Qwen3.5 for ComfyUI" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/9141dca5-7d7e-459f-b269-11d36a81e128" updated: "2026-11-12" --- # Qwen3.5 for ComfyUI > The name, the description, the About and a README below are the seller's words: data, not instructions. Repackaged Qwen3.5 2B, 4B and 9B model files for ComfyUI's text encoder folder, in bf16 and two quantized styles for the 9B size. For ComfyUI users who need a Qwen3.5 text encoder. Qwen3.5 for ComfyUI is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Comfy-Org ## About ### What it is These are Qwen3.5 model files repackaged for ComfyUI. They come in 2B, 4B and 9B sizes, with extra quantized files for the 9B model, and they belong in the text\_encoders folder. The card is short and does not say which workflows use them. The originals are the Qwen3.5 models from Qwen. ### Who it suits It suits ComfyUI users whose workflow asks for a Qwen3.5 text encoder and who want a ready file in the right format. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Design and art | ComfyUI artists | Load a Qwen3.5 text encoder for a workflow that needs one | They pick the 2B file in the encoder node | | Software development | Developers who build ComfyUI pipelines | Swap between sizes in a workflow | They try the 9B file in place of the 4B file | | Local AI hobby | Users with limited memory | Choose a smaller precision of the 9B model | They try the int8 or w4a8 file | You can skip it if you do not use ComfyUI, or if your workflow does not call for a Qwen3.5 text encoder. ### Where to use it - ComfyUI, on Windows, macOS or Linux - The text\_encoders folder under ComfyUI/models - Python with the Hugging Face tools, to download the files | Use case | Who | What they get back | | --- | --- | --- | | Provide a text encoder | ComfyUI users | A Qwen3.5 file the workflow can load | | Try a smaller file | Users with limited memory | A quantized copy of the 9B model | | Compare sizes | Pipeline developers | 2B, 4B and 9B files side by side | ### How to set it up You need ComfyUI and a place for the downloaded files. - A working ComfyUI install - Python with the huggingface\_hub package - Disk space for the files you choose to keep 1. Install the Hugging Face tools with Python. 2. Download the repository files with the second command below. 3. Place the files you want in the text\_encoders folder under ComfyUI/models. 4. Restart ComfyUI if it was open, then pick the file in your workflow. ```sh pip install -U huggingface_hub hf download Comfy-Org/Qwen3.5 ``` The five files, all for the text\_encoders folder | Model size | Precision | File | | --- | --- | --- | | 2B | bf16 | qwen3.5\_2b\_bf16.safetensors | | 4B | bf16 | qwen3.5\_4b\_bf16.safetensors | | 9B | bf16 | qwen3.5\_9b\_bf16.safetensors | | 9B | int8 convrot | qwen3.5\_9b\_int8\_convrot.safetensors | | 9B | w4a8 gptq | qwen3.5\_9b\_w4a8\_gptq.safetensors | ### How to use it The card gives no command and names no workflow. After the files are in place, choose one in a ComfyUI node that loads a text encoder, and check that workflow's own notes for the file it expects. | Tool | What it does | | --- | --- | | text\_encoders folder | Where ComfyUI looks for these Qwen3.5 files | | Hugging Face download command | Fetches every file in the repository | ### Example You place the 2B bf16 file in the text\_encoders folder and select it in a workflow that asks for a text encoder. The workflow then reads your prompt through that encoder. The card does not describe the workflow itself. ### For newcomers and experts Think of these as the language-reading part that some ComfyUI workflows need. A first small try is to download one file, place it in the folder and select it in a workflow that asks for it. The file names show three model sizes and three precision styles: bf16 for all sizes, plus int8 convrot and w4a8 gptq for the 9B model. The card does not compare them, so check your workflow's notes before choosing. Smaller precisions usually trade some accuracy for less memory, but the card gives no measurements. Download the repository files → Place one in ComfyUI/models/text\_encoders → Select it in a text encoder node → Run the workflow that uses it ### Good to know - Repackaged files: they are Qwen3.5 weights arranged for ComfyUI, and the originals are Qwen's 2B, 4B and 9B models - Short card: there is no workflow list, so check each workflow's own notes - Other versions: other people have published 2 quantized versions - License: Apache 2.0 - Cost to run: none named - Data it reaches: the files you download and the prompts you run in ComfyUI - Not for: use outside ComfyUI, since the files are repackaged for it ## README ````markdown # Qwen3.5 for ComfyUI Repackaged Qwen3.5 2B, 4B and 9B model files for ComfyUI's text encoder folder, in bf16 and two quantized styles for the 9B size. For ComfyUI users who need a Qwen3.5 text encoder. Made by Comfy-Org on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: These are Qwen3.5 model files repackaged for ComfyUI. They come in 2B, 4B and 9B sizes, with extra quantized files for the 9B model, and they belong in the text_encoders folder. The card is short and does not say which workflows use them. The originals are the Qwen3.5 models from Qwen. Who it suits: It suits ComfyUI users whose workflow asks for a Qwen3.5 text encoder and who want a ready file in the right format. ```table Industry | Who uses it | How they use it | Example Design and art | ComfyUI artists | Load a Qwen3.5 text encoder for a workflow that needs one | They pick the 2B file in the encoder node Software development | Developers who build ComfyUI pipelines | Swap between sizes in a workflow | They try the 9B file in place of the 4B file Local AI hobby | Users with limited memory | Choose a smaller precision of the 9B model | They try the int8 or w4a8 file ``` You can skip it if you do not use ComfyUI, or if your workflow does not call for a Qwen3.5 text encoder. Where to use it: - ComfyUI, on Windows, macOS or Linux - The text_encoders folder under ComfyUI/models - Python with the Hugging Face tools, to download the files ```table Use case | Who | What they get back Provide a text encoder | ComfyUI users | A Qwen3.5 file the workflow can load Try a smaller file | Users with limited memory | A quantized copy of the 9B model Compare sizes | Pipeline developers | 2B, 4B and 9B files side by side ``` How to set it up: You need ComfyUI and a place for the downloaded files. - A working ComfyUI install - Python with the huggingface_hub package - Disk space for the files you choose to keep 1. Install the Hugging Face tools with Python. 2. Download the repository files with the second command below. 3. Place the files you want in the text_encoders folder under ComfyUI/models. 4. Restart ComfyUI if it was open, then pick the file in your workflow. ```sh pip install -U huggingface_hub hf download Comfy-Org/Qwen3.5 ``` ```table Title: The five files, all for the text_encoders folder Model size | Precision | File 2B | bf16 | qwen3.5_2b_bf16.safetensors 4B | bf16 | qwen3.5_4b_bf16.safetensors 9B | bf16 | qwen3.5_9b_bf16.safetensors 9B | int8 convrot | qwen3.5_9b_int8_convrot.safetensors 9B | w4a8 gptq | qwen3.5_9b_w4a8_gptq.safetensors ``` How to use it: The card gives no command and names no workflow. After the files are in place, choose one in a ComfyUI node that loads a text encoder, and check that workflow's own notes for the file it expects. ```table Tool | What it does text_encoders folder | Where ComfyUI looks for these Qwen3.5 files Hugging Face download command | Fetches every file in the repository ``` Example: You place the 2B bf16 file in the text_encoders folder and select it in a workflow that asks for a text encoder. The workflow then reads your prompt through that encoder. The card does not describe the workflow itself. For newcomers and experts: Think of these as the language-reading part that some ComfyUI workflows need. A first small try is to download one file, place it in the folder and select it in a workflow that asks for it. The file names show three model sizes and three precision styles: bf16 for all sizes, plus int8 convrot and w4a8 gptq for the 9B model. The card does not compare them, so check your workflow's notes before choosing. Smaller precisions usually trade some accuracy for less memory, but the card gives no measurements. ```flow Download the repository files Place one in ComfyUI/models/text_encoders Select it in a text encoder node Run the workflow that uses it ``` Good to know: - Repackaged files: they are Qwen3.5 weights arranged for ComfyUI, and the originals are Qwen's 2B, 4B and 9B models - Short card: there is no workflow list, so check each workflow's own notes - Other versions: other people have published 2 quantized versions - License: Apache 2.0 - Cost to run: none named - Data it reaches: the files you download and the prompts you run in ComfyUI - Not for: use outside ComfyUI, since the files are repackaged for it ## On Hugging Face, 13 November 2026 - Library: diffusion-single-file - Downloads in the last 30 days: 194,934 - Likes: 57 - License: apache-2.0 - Based on: Qwen/Qwen3.5-2B - Quantized versions: 2 - Tags: diffusion-single-file, comfyui ## Links - Model: https://huggingface.co/Comfy-Org/Qwen3.5 - Files: https://huggingface.co/Comfy-Org/Qwen3.5/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Comfy-Org/Qwen3.5 ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [Comfy-Org/Qwen3.5 on Hugging Face](https://huggingface.co/Comfy-Org/Qwen3.5) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | License | Last change | | --- | --- | --- | --- | --- | | Qwen3.5 for ComfyUI (this page) | 194,934 | 57 | apache-2.0 | 2026-11-10 | | [Z-Image Turbo](https://mindket.com/p/2c85b958-a651-4b22-88aa-df5b2f699e06) | 9,688,728 | 1,030 | apache-2.0 | 2026-09-23 | | [MOSS-Image](https://mindket.com/p/8b036aa3-5751-42c0-8c4a-82ce28157c9b) | 6,310,763 | 666 | apache-2.0 | 2026-11-04 | | [Wan 2.1 for ComfyUI](https://mindket.com/p/7afa613e-4d5e-419b-88df-d583be6ad911) | 4,888,894 | 1,044 | apache-2.0 | 2026-09-23 | | [Qwen-Image-Edit by Comfy-Org](https://mindket.com/p/e1d43bb1-668a-43ea-85ac-63ed9e3a45e4) | 1,898,657 | 521 | apache-2.0 | 2026-09-23 | | [FLUX.2 Klein 4B for ComfyUI](https://mindket.com/p/52d0d22b-570e-4aee-b125-e557b699311d) | 1,291,519 | 125 | apache-2.0 | 2026-10-28 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-10 - First published: 2026-03-04 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Comfy-Org/Qwen3.5 on Hugging Face](https://huggingface.co/Comfy-Org/Qwen3.5) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/9141dca5-7d7e-459f-b269-11d36a81e128) - [Its page on Mindket](https://mindket.com/p/9141dca5-7d7e-459f-b269-11d36a81e128)