Qwen-Image-2.1
Qwen-Image-2.1 (Text to image) needs 9.5 GB of VRAM in ComfyUI, at the prompt enhancer of its own template, by file sizes read 3 November 2026. The smallest card that loads it with room to work is the RTX 5070 (12 GB), and the template downloads 26.8 GB.
- Made by
- Qwen (Alibaba)
- Licence
- Qwen Research License
- Released
- September 2026
- Sizes read
- 3 November 2026
Largest stage from exact file sizes, with ComfyUI's own template; LoRAs are not counted. Working memory for the generation comes on top. Open it in the ComfyUI checker
Largest stage from exact file sizes, with ComfyUI's own template; LoRAs are not counted. Working memory for the generation comes on top. Open it in the ComfyUI checker
Which file on your card
For each memory size, the best file for that card: the highest-precision diffusion file that loads with room to work (one that only just fits when nothing else does), and what is left for working memory while it samples. On a larger card that can be above the file ComfyUI's template loads, which the answer above is about. "Streams" means even the smallest file is larger than the card: ComfyUI still runs it from system RAM, more slowly. FP4 files go only to the Blackwell cards that run them natively.
Text to image
ComfyUI's template for Text to image: INT8 ConvRot diffusion model, INT8 ConvRot text encoder. Stages: text encoder 9.4 GB, prompt enhancer 9.5 GB, diffusion 7.9 GB. Download 26.8 GB.
Computed 3 November 2026Turbo, 8 steps
ComfyUI's template for Turbo, 8 steps: INT8 ConvRot diffusion model, INT8 ConvRot text encoder. Stages: text encoder 9.4 GB, prompt enhancer 9.5 GB, diffusion 7.9 GB. Download 26.8 GB.
Computed 3 November 2026Check another card, or pick a file by hand, in the ComfyUI VRAM checker. Built your own workflow around it, with LoRAs or custom nodes? Drop it into the ComfyUI workflow checker.
Where to run it
Text to image
On-demand prices before tax, read 19 October 2026.
Turbo, 8 steps
On-demand prices before tax, read 19 October 2026.
About the model
Qwen-Image-2.1 is Qwen's open image model. Qwen's image model from September 2026: a 7-billion-parameter generator with native 2K output, driven by an 8-billion-parameter Qwen3-VL text encoder. Its text side, the encoder plus the 9-billion-parameter prompt rewriter in ComfyUI's template, is larger than the image generator, and that is what decides the memory.
Text to image: 7.1B · Turbo, 8 steps: 7.1B Text encoder: Qwen3-VL 8B Qwen Research License Released September 2026
Before you download
Research and evaluation only; commercial use needs a separate licence from Qwen. Read the Qwen Research License itself before using it for work.
Good at
- Native 2K images.
- The same files run ComfyUI's image-edit template as well as text to image.
- INT8 files at about half the size of BF16.
- Turbo (October 2026): an accelerated checkpoint that makes images and edits in 8 denoising steps, with files the same size as the original's.
Watch out for
- The Qwen Research License allows research and evaluation only. Commercial use needs a separate licence from Qwen.
- The prompt rewriter is a separate language model that ComfyUI's template loads by default.
- Qwen publishes no VRAM figure.
Every Qwen-Image-2.1 file ComfyUI loads
Sizes are the exact byte counts Hugging Face reports, read 3 November 2026. Files marked "template" are the ones ComfyUI's official workflow downloads.
| Part | Precision | Size | Version | File |
|---|---|---|---|---|
| Diffusion model | BF16 | 14.23 GB | Text to image | qwen_image_2.1_bf16.safetensors |
| Diffusion model | INT8 ConvRot · template | 7.26 GB | Text to image | qwen_image_2.1_int8_convrot.safetensors |
| Diffusion model | BF16 | 14.23 GB | Turbo, 8 steps | qwen_image_2.1_turbo_bf16.safetensors |
| Diffusion model | INT8 ConvRot · template | 7.26 GB | Turbo, 8 steps | qwen_image_2.1_turbo_int8_convrot.safetensors |
| Text encoder | BF16 | 17.53 GB | all | qwen3vl_8b_bf16.safetensors |
| Text encoder | INT8 ConvRot · template | 9.35 GB | all | qwen3vl_8b_int8_convrot.safetensors |
| Text encoder | W4A8 | 6.31 GB | all | qwen3vl_8b_w4a8.safetensors |
| Prompt enhancer | INT8 ConvRot · template | 9.47 GB | all | qwen3.5_9b_qwen_image_2.1_pe_t2i.int8_convrot.safetensors |
| VAE | BF16 · template | 0.68 GB | all | qwen_image_2.1_vae_bf16.safetensors |
What Qwen says it needs
Qwen states no VRAM figure on the model card or in its GitHub README. The closest it comes: "With just 7B parameters in its visual generation component" (source).
Those figures and this page measure different things. A vendor's figure covers its own script at its default resolution, working memory included. This page counts the weights each stage holds, which is exact, and leaves the working memory as the space that remains, because it depends on your resolution and attention kernel and nobody publishes it per model. If generation runs out of memory with a file that loads, lower the resolution before stepping down a precision. ComfyUI's README says it "can run even the biggest open source models on as low as 4GB vram + 8GB ram" by streaming weights (source), so "streams" means slower, not impossible.
LoRA training for Qwen-Image-2.1
No trainer we checked publishes a VRAM figure for training Qwen-Image-2.1 yet (kohya's sd-scripts and musubi-tuner, ostris' ai-toolkit, diffusion-pipe, and Qwen's own repo). When one does, it goes here.
Questions
- How much VRAM does Qwen-Image-2.1 need?
- In ComfyUI's own workflow for Text to image, the largest stage is the prompt enhancer at 9.5 GB, and the whole workflow downloads 26.8 GB. Working memory for generation comes on top and grows with resolution. Qwen publishes no VRAM figure.
- Can I run Qwen-Image-2.1 on 8 GB of VRAM?
- Not fully. The smallest file here, INT8 ConvRot at 7.3 GB, needs 9.5 GB at its largest stage, more than 8 GB holds. ComfyUI will still run it by streaming weights from system RAM, which works but is slower.
- Can I run Qwen-Image-2.1 on 12 GB of VRAM?
- Yes, with the INT8 ConvRot file: its largest stage, the prompt enhancer, is 9.5 GB, which loads on 12 GB with 4.1 GB left for working memory.
- Can I run Qwen-Image-2.1 on 16 GB of VRAM?
- Yes, with the INT8 ConvRot file: its largest stage, the prompt enhancer, is 9.5 GB, which loads on 16 GB with 8.1 GB left for working memory.
- Which Qwen-Image-2.1 file should I download?
- The highest precision that loads fully on your card. On a 24 GB card that is the BF16 file (14.2 GB). ComfyUI's template downloads INT8 ConvRot with the INT8 ConvRot text encoder. FP4 files (NVFP4) are made for Blackwell cards (RTX 50, RTX PRO 6000, DGX Spark); on older cards, use FP8 or INT8.
- Files and sizes: Comfy-Org/Qwen-Image-2.1 on Hugging Face, read from the Hugging Face API. Template files: ComfyUI's Qwen-Image-2.1 guide.
- Model and licence: Qwen/Qwen-Image-2.1 and the Qwen Research License.
- Card memory: manufacturers' specifications, as on each GPU page. The checker covers NVIDIA cards; ComfyUI also runs on AMD and Apple silicon, where file formats and speed differ and we have not sized them.
- Fit rule: a stage loads fully under 85% of usable memory and is tight up to 95%, the same margins the LLM pages use.
- Prices: each provider's own pricing page, on the dates beside them.