| File | flux1-kontext-dev-Q8_0.gguf |
| Model | FLUX.1 Kontext [dev] (image model, 12B) |
| Precision | Q8_0 |
| Size | 12.7 GB |
| VRAM to fit | about 15.3 GB |
| Folder | ComfyUI/models/unet/ |
| Loader node | Unet Loader (GGUF) from the ComfyUI-GGUF custom nodes |
| Source | QuantStack/FLUX.1-Kontext-dev-GGUF on Hugging Face |
Download flux1-kontext-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 9.3 GB | flux1-kontext-dev-Q3_K_M.gguf (5.4 GB) |
| 8 GB | Offload only | Short by 7.3 GB: runs with part of it in system RAM, slower | flux1-kontext-dev-Q3_K_M.gguf (5.4 GB) |
| 10 GB | Offload only | Short by 5.3 GB: runs with part of it in system RAM, slower | flux1-kontext-dev-Q4_K_M.gguf (6.9 GB) |
| 12 GB | Offload only | Short by 3.3 GB: runs with part of it in system RAM, slower | flux1-kontext-dev-Q5_K_M.gguf (8.4 GB) |
| 16 GB | Runs well | Fits in VRAM, 0.7 GB to spare | flux1-dev-kontext_fp8_scaled.safetensors (11.9 GB) |
| 20 GB | Runs well | Fits in VRAM, 4.7 GB to spare | flux1-dev-kontext_fp8_scaled.safetensors (11.9 GB) |
| 24 GB | Runs well | Fits in VRAM, 8.7 GB to spare | flux1-dev-kontext_fp8_scaled.safetensors (11.9 GB) |
| 32 GB | Runs well | Fits in VRAM, 16.7 GB to spare | flux1-kontext-dev.safetensors (23.8 GB) |
| 48 GB | Runs well | Fits in VRAM, 32.7 GB to spare | flux1-kontext-dev.safetensors (23.8 GB) |
Need = file × 1 + 1.8 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 | 82.1 s per image | 1024x1024 | 20 | 15.5 GB | measured by me, 2026-10-11 |
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-kontext-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 Kontext page.
Other files of FLUX.1 Kontext
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| flux1-kontext-dev.safetensors | 16-bit | 23.8 GB | 26.4 GB |
| flux1-kontext-dev-Q8_0.gguf | Q8_0 | 12.7 GB | 15.3 GB |
| flux1-dev-kontext_fp8_scaled.safetensors | FP8 | 11.9 GB | 14.5 GB |
| flux1-kontext-dev-Q6_K.gguf | Q6_K | 9.8 GB | 12.4 GB |
| flux1-kontext-dev-Q5_K_M.gguf | Q5_K_M | 8.4 GB | 11.0 GB |
| flux1-kontext-dev-Q4_K_M.gguf | Q4_K_M | 6.9 GB | 9.5 GB |
| flux1-kontext-dev-Q3_K_M.gguf | Q3_K_M | 5.4 GB | 8.0 GB |
| flux1-kontext-dev-Q2_K.gguf | Q2_K | 4.0 GB | 6.6 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 Kontext [dev] — GGUF Q8_0 — 82.1 s per edit (1024×1024)
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).