| File | flux1-dev-Q8_0.gguf |
| Model | FLUX.1 [dev] (image model, 12B) |
| Precision | Q8_0 |
| Size | 12.7 GB |
| VRAM to fit | about 15.0 GB |
| Folder | ComfyUI/models/unet/ |
| Loader node | Unet Loader (GGUF) from the ComfyUI-GGUF custom nodes |
| Source | city96/FLUX.1-dev-gguf on Hugging Face |
Download flux1-dev-Q8_0.gguf (12.7 GB)
Where to put it
Put the file in ComfyUI/models/unet/ (portable version: ComfyUI_windows_portable/ComfyUI/models/unet/). Press R in ComfyUI or restart it, then pick the file in Unet Loader (GGUF) from the ComfyUI-GGUF custom nodes.
If a workflow says “Value not in list” for that node, the workflow expects a file with another name. Click the node and choose this one.
Which graphics cards it fits
| VRAM | This file | Best file for that card (RTX 40/50) | |
|---|---|---|---|
| 6 GB | Not practical | Short by 9.0 GB | flux1-dev-Q3_K_S.gguf (5.2 GB) |
| 8 GB | Offload only | Short by 7.0 GB: runs with part of it in system RAM, slower | flux1-dev-Q3_K_S.gguf (5.2 GB) |
| 10 GB | Offload only | Short by 5.0 GB: runs with part of it in system RAM, slower | flux1-dev-Q4_K_S.gguf (6.8 GB) |
| 12 GB | Offload only | Short by 3.0 GB: runs with part of it in system RAM, slower | flux1-dev-Q5_K_S.gguf (8.3 GB) |
| 16 GB | Runs well | Fits in VRAM, 1.0 GB to spare | flux1-dev-fp8-e4m3fn.safetensors (11.9 GB) |
| 20 GB | Runs well | Fits in VRAM, 5.0 GB to spare | flux1-dev-fp8-e4m3fn.safetensors (11.9 GB) |
| 24 GB | Runs well | Fits in VRAM, 9.0 GB to spare | flux1-dev-fp8-e4m3fn.safetensors (11.9 GB) |
| 32 GB | Runs well | Fits in VRAM, 17.0 GB to spare | flux1-dev.safetensors (23.8 GB) |
| 48 GB | Runs well | Fits in VRAM, 33.0 GB to spare | flux1-dev.safetensors (23.8 GB) |
Need = file × 1 + 1.5 GB for the picture and 0.8 GB for Windows and the browser — the same rule as the rest of the site.
Measured with this exact file
| GPU | Time | Size | Steps | Peak VRAM | Source |
|---|---|---|---|---|---|
| RTX 5060 Ti 16 GB | 40.6 s per image | 1024x1024 | 20 | 15.1 GB | measured by me, 2026-09-27 |
Time = sampling + VAE decode, after a warm-up run. Peak VRAM = memory in use on the whole card. How I measure.
What else you need
This file alone does not make a picture. With it you load:
| Role | File | Size | Folder |
|---|---|---|---|
| Model | flux1-dev-Q8_0.gguf | 12.7 GB | models/unet |
| Text encoder | t5xxl_fp8_e4m3fn.safetensors | 4.9 GB | models/text_encoders |
| Text encoder | clip_l.safetensors | 0.2 GB | models/text_encoders |
| VAE | ae.safetensors | 0.3 GB | models/vae |
18.2 GB in total. Smaller text-encoder versions and other options are on the FLUX.1 dev page.
Other files of FLUX.1 dev
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| flux1-dev.safetensors | 16-bit | 23.8 GB | 26.1 GB |
| flux1-dev-Q8_0.gguf | Q8_0 | 12.7 GB | 15.0 GB |
| flux1-dev-fp8-e4m3fn.safetensors | FP8 | 11.9 GB | 14.2 GB |
| flux1-dev-Q6_K.gguf | Q6_K | 9.9 GB | 12.2 GB |
| flux1-dev-Q5_K_S.gguf | Q5_K_S | 8.3 GB | 10.6 GB |
| flux1-dev-Q4_K_S.gguf | Q4_K_S | 6.8 GB | 9.1 GB |
| flux1-dev-Q3_K_S.gguf | Q3_K_S | 5.2 GB | 7.5 GB |
| flux1-dev-Q2_K.gguf | Q2_K | 4.0 GB | 6.3 GB |
Same model, different compression. 8-bit files (FP8, INT8, Q8_0) look almost the same as 16-bit; below Q5 the loss starts to show.
Free workflow with this file
- FLUX.1 [dev] — GGUF Q8_0 — 40.6 s per 1024×1024 image
Drag the .json into ComfyUI. All free workflows →
Want the answer for your exact card? Check your GPU. Every file of every model: ComfyUI model files.
Size and source read from Hugging Face (2026-10-01).