Mage-Flow (Microsoft) on 6 GB of VRAM
Download INT8 (4.2 GB). With the model's working memory it needs about 6.0 GB, leaving 0.0 GB spare on 6 GB. Quality: practically identical to the original.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | mage_flow_int8_convrot.safetensors INT8 · Comfy-Org/Mage-Flow | models/diffusion_models | 4.2 GB | Download → |
| Text encoder | qwen3vl_4b_bf16.safetensors Qwen3-VL 4B BF16 · Comfy-Org/Mage-Flow | models/text_encoders | 8.9 GB | Download → |
| VAE | mage_flow_vae_bf16.safetensors Mage-Flow VAE · Comfy-Org/Mage-Flow | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 13.4 GB | |||
Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.
System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 13.4 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 19.4 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every file, on 6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 8.2 GB | 10.0 GB | 4.0 GB too big | the original weights | Hugging Face → |
| INT8 ← SAFETENSORS · Comfy-Org | 4.2 GB | 6.0 GB | fits · 0.0 GB spare | practically identical to the original | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
Qwen3-VL 4B: 8.9 GB as 16-bit, 5.2 GB as FP8. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 6 GB the encoder itself is too big for VRAM, so let it run from system RAM: slower prompt encoding, same images.