abenzerps/Qwen-Image-2.1-Turbo-Quantized

Qwen-Image-2.1 Turbo Quantized

GGUF, Safetensors, and MLX quantized formats of Qwen/Qwen-Image-2.1-Turbo for local image generation using the official turbo base weights.

Benchmark

Turbo Quantized Files

Quantization	File	Size
FP8	qwen-image-2.1-turbo-fp8.safetensors	6.63 GB
INT8 ConvRot	qwen-image-2.1-turbo-int8_convrot.safetensors	6.76 GB
NVFP4	qwen-image-2.1-turbo-NVFP4.safetensors	4.20 GB
MLX 4-bit	qwen-image-2.1-turbo-MLX-4bit.safetensors	4.00 GB
MLX 6-bit	qwen-image-2.1-turbo-MLX-6bit.safetensors	5.78 GB
MLX 8-bit	qwen-image-2.1-turbo-MLX-8bit.safetensors	7.56 GB
Q8_0	qwen-image-2.1-turbo-Q8_0.gguf	7.59 GB
Q6_K	qwen-image-2.1-turbo-Q6_K.gguf	5.88 GB
Q5_K_M	qwen-image-2.1-turbo-Q5_K_M.gguf	4.94 GB
Q4_K_M	qwen-image-2.1-turbo-Q4_K_M.gguf	4.05 GB
Q4_0	qwen-image-2.1-turbo-Q4_0.gguf	4.05 GB

Q4_K_M is recommended for the best balance of size and quality for GGUF. INT8 ConvRot and NVFP4 offer high performance on supported GPUs, while MLX formats are optimized for Apple Silicon.

Text Encoders & VAE

Companion model files packaged for ComfyUI:

Type	File	Precision	Size
Text Encoder	text_encoders/qwen3vl_8b_bf16.safetensors	BF16	17.53 GB
Text Encoder	text_encoders/qwen3vl_8b_int8_convrot.safetensors	Int8	9.35 GB
VAE	vae/qwen_image_2.1_vae_bf16.safetensors	BF16	676 MB

Usage

Use the model with ComfyUI and ComfyUI-GGUF.

All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository.

1. Download & File Placement

Download the files and place them in their respective ComfyUI directories:

ComfyUI/
└── models/
    ├── diffusion_models/
    │   └── qwen-image-2.1-turbo-Q4_K_M.gguf      # Or fp8 / int8_convrot / NVFP4 .safetensors
    ├── text_encoders/
    │   └── qwen3vl_8b_bf16.safetensors        # Or qwen3vl_8b_int8_convrot.safetensors (recommended for lower memory)
    └── vae/
        └── qwen_image_2.1_vae_bf16.safetensors

2. ComfyUI Setup

1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning leejet/ComfyUI-GGUF into your custom nodes:

   cd ComfyUI/custom_nodes
   git clone https://github.com/leejet/ComfyUI-GGUF
   

2. Node Configuration:
   • Diffusion Model: Add the Unet Loader (GGUF) node (for .gguf files) or standard UNETLoader (for .safetensors files) and select your downloaded model.
   • Text Encoder: Add the standard CLIPLoader node, select qwen3vl_8b_bf16.safetensors (or int8), and set type to qwen_image.
   • VAE: Add the standard VAELoader node and select qwen_image_2.1_vae_bf16.safetensors.
3. Official Workflows:
   • You can use the official Comfy-Org workflow templates: Text-to-Image or Image Edit.

Memory & Performance Notes

• Optimal Setup (GPU + RAM): Keep the GGUF / Quantized diffusion model in GPU VRAM and let the text encoder run in / offload to System RAM (CPU).
• Low VRAM Mode: If you experience VRAM out-of-memory errors, start ComfyUI with the --lowvram argument.

Source and build

• Source model: Qwen/Qwen-Image-2.1-Turbo
• Text encoder & VAE source: Comfy-Org/Qwen-Image-2.1
• Conversion: stable-diffusion.cpp & comfy-kitchen
• License: Qwen Research License
• Checksums: SHA256SUMS