Can the Arc B580 12 GB run Mage-Flow (Microsoft)?
Download 16-bit (8.2 GB). With the model's working memory it needs about 10.0 GB, leaving 2.0 GB spare on 12 GB. Quality: the original weights.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | mage_flow_bf16.safetensors 16-bit · Comfy-Org/Mage-Flow | models/diffusion_models | 8.2 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 | 17.5 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 17.5 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 23.5 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every Mage-Flow file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · Comfy-Org | 8.2 GB | 10.0 GB | fits · 2.0 GB spare | the original weights | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 4.2 GB | 6.0 GB | fits · 6.0 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 12 GB the FP8 encoder fits on its own, so prompt encoding stays fast.
04About this GPU
Intel Arc GPUs run ComfyUI through PyTorch's native XPU support on Windows 11 and Linux. Memory works the same as on NVIDIA, so the fit verdicts apply. FP8 files save memory but give no speed-up, and some custom nodes are NVIDIA-only.
Arc B580 12 GB: 12 GB GDDR6 · 192-bit · 456 GB/s · Battlemage. Everything that runs on the Arc B580 12 GB →
05What more VRAM would change
Nothing to gain for this model: the Arc B580 12 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.
What changes from the Arc B580 12 GB to the RTX 5060 Ti 16 GB →
06Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Mage-Flow on a Arc B580 12 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
How much VRAM does Mage-Flow need?
Around 6.0 GB with the smallest file (INT8) and 6.0 GB with an 8-bit file (INT8), counting working memory and a small system reserve. The full 16-bit file needs about 10.0 GB.
Which Mage-Flow file should I download for the Arc B580 12 GB?
16-bit (8.2 GB) from Comfy-Org/Mage-Flow.
Is FP8 faster than GGUF on the Arc B580 12 GB?
No. This GPU has no FP8 compute, so ComfyUI converts FP8 weights back before the maths. FP8 only saves memory here; Q8_0 GGUF is the closer-to-original 8-bit pick.
How much do I need to download for Mage-Flow on the Arc B580 12 GB?
About 17.5 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 12 GB card, 32 GB of system RAM or more is recommended.