Can the Arc B580 12 GB run FLUX.2 [dev]?
Not entirely. Even Q4_K_M is 11.4 GB over 12 GB, so ComfyUI keeps part of it in system RAM.
The smallest sensible file, Q4_K_M (20.1 GB), needs about 23.4 GB - 11.4 GB more than Arc B580 12 GB has. ComfyUI can still run it by streaming part of the model from system RAM. How much slower that is depends on your ComfyUI version, the file format and the PCIe link - see the note below.
01With more VRAM
With 48 GB you could run FLUX.2 dev at 8-bit or better (Q8_0, 35.0 GB) with no offloading.
What changes from the Arc B580 12 GB to the RTX 5060 Ti 16 GB →
02Every FLUX.2 dev file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 64.4 GB | 67.7 GB | 55.7 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 35.0 GB | 38.3 GB | 26.3 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 35.5 GB | 38.8 GB | 26.8 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 27.4 GB | 30.7 GB | 18.7 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 24.1 GB | 27.4 GB | 15.4 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · city96 | 20.1 GB | 23.4 GB | 11.4 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 16.0 GB | 19.3 GB | 7.3 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 12.9 GB | 16.2 GB | 4.2 GB too big | heavy loss; a last resort | Hugging Face → |
“Needed” adds 2.5 GB of working memory for FLUX.2 dev and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux2-dev-Q4_K_M.gguf Q4_K_M · city96/FLUX.2-dev-gguf | models/unet | 20.1 GB | Download → |
| Text encoder | mistral_3_small_flux2_fp8.safetensors Mistral 3 Small FP8 · Comfy-Org/flux2-dev | models/text_encoders | 18.0 GB | Download → |
| VAE | flux2-vae.safetensors FLUX.2 VAE · Comfy-Org/flux2-dev | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 38.5 GB | |||
Alternatives: Mistral 3 Small BF16 (35.6 GB). Sizes from Hugging Face, 2026-10-01.
System RAM: 48 GB or more. These files take about 38.5 GB of RAM while loaded, 44.5 GB with Windows and ComfyUI. What happens with less. calculated
04The text encoder
At 18.0 GB even the smallest Mistral Small 3 (24B) file is too big for 12 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 35.6 GB, FP8 18.0 GB. Why the encoder does not count against VRAM →
05Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run FLUX.2 dev on a Arc B580 12 GB, send your time per image and peak VRAM and it will appear here, credited.
06About the Arc B580 12 GB
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.
12 GB GDDR6 · 192-bit · 456 GB/s · Battlemage. Everything that runs on it →
07Questions
How much VRAM does FLUX.2 dev need?
Around 16.2 GB with the smallest file (Q2_K) and 38.8 GB with an 8-bit file (FP8). The full 16-bit file needs about 67.7 GB.
Which FLUX.2 dev file should I download for the Arc B580 12 GB?
Q4_K_M (20.1 GB) from city96/FLUX.2-dev-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for FLUX.2 dev on the Arc B580 12 GB?
Q8_0 (35.0 GB). The Arc B580 12 GB has no FP8 maths, so FP8 (35.5 GB) only saves memory and is a step further from the original.
How much do I need to download for FLUX.2 dev on the Arc B580 12 GB?
38.5 GB: flux2-dev-Q4_K_M.gguf, mistral_3_small_flux2_fp8.safetensors, flux2-vae.safetensors.