Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Mage-Flow (Microsoft) on 6 GB of VRAM

Image model · 4.12BAny 6 GB GPUData 2026-09-25
Runs well
Yes — and comfortably.

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.

Best fileINT8
File size4.2 GB
VRAM needed~6.0 GB
System RAM32 GB+
Memory map · 6 GB GPU6.0 GB / 6 GB
03 GB6 GB
Weights INT8 · 4.2 GBWorking memory · 1.0 GBReserve · 0.8 GBFree · 0.0 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What to download

PartFileFolderSize
Modelmage_flow_int8_convrot.safetensors
INT8 · Comfy-Org/Mage-Flow
models/diffusion_models4.2 GBDownload →
Text encoderqwen3vl_4b_bf16.safetensors
Qwen3-VL 4B BF16 · Comfy-Org/Mage-Flow
models/text_encoders8.9 GBDownload →
VAEmage_flow_vae_bf16.safetensors
Mage-Flow VAE · Comfy-Org/Mage-Flow
models/vae0.3 GBDownload →
Total download · keep about the same free on disk13.4 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

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
8.2 GB10.0 GB4.0 GB too bigthe original weightsHugging Face →
INT8 ←
SAFETENSORS · Comfy-Org
4.2 GB6.0 GBfits · 0.0 GB sparepractically identical to the originalHugging 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.