Mage-Flow (Microsoft) VRAM requirements

01The files, and how much VRAM each needs

“Needed” = file + 1 GB working memory + 0.8 GB system reserve.

02By amount of VRAM

03Best GPU for Mage-Flow

The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for Mage-Flow → Planning bigger images or longer clips? Open the calculator →

04By graphics card

On RTX 40/50 GPUs the FP8 file is preferred over Q8_0 when both fit (hardware FP8). All verdicts are calculated; see how the numbers work.

05Text encoder, VAE and other files

The files the official ComfyUI workflows load next to the model. Sizes read from Hugging Face (2026-09-25). Every GPU page for this model lists the exact set to download for that card, with the total.

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 16 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

06Where the files go in ComfyUI

Standard ComfyUI folders. After copying files, press R in ComfyUI (or restart it) to refresh the lists. Some uploads need their uploader's own loader node — see the notes above.

07AMD, Intel and NVIDIA: which file types are fast

Every file type loads on every listed GPU, so the memory verdicts apply to all of them. What differs is speed: FP8 maths needs RTX 40/50 or RX 9000 (with ROCm 6.4+ and PyTorch 2.7+); ComfyUI's INT8 maths runs on NVIDIA and AMD, not on Intel; GGUF is unpacked on the fly on any GPU, which costs some speed. NVFP4 files are fast only on RTX 50. AMD runs ComfyUI on Windows through ROCm, Intel through PyTorch XPU; some custom nodes are NVIDIA-only. Source: ComfyUI model_management.py. AMD and Intel guide →

08Measured and reported results

No measured results yet. Send yours.

09Training a LoRA for Mage-Flow

No trainer documentation with a VRAM figure for this model was found yet. What the trainers say for other models →

10Every file tracked for Mage-Flow

4.1B NR-MMDiT (HF API 4,115,745,408 BF16), native-resolution rectified flow. Plain 'mage_flow' = RL-aligned (20 steps), base = 30 steps, turbo = 4 steps; edit/edit-base/edit-turbo are separate instruction-edit checkpoints. VAE: mage_flow_vae_bf16 (345053056), own one-step Mage-VAE. Native ComfyUI support (docs.comfy.org workflow). Official weights under mage-flow-community org.