| File | flux-2-klein-9b-Q8_0.gguf |
| Model | FLUX.2 [klein] 9B (image model, 9B) |
| Precision | Q8_0 |
| Size | 10.0 GB |
| VRAM to fit | about 12.3 GB |
| Folder | ComfyUI/models/unet/ |
| Loader node | Unet Loader (GGUF) from the ComfyUI-GGUF custom nodes |
| Source | unsloth/FLUX.2-klein-9B-GGUF on Hugging Face |
Download flux-2-klein-9b-Q8_0.gguf (10.0 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 | Offload only | Short by 6.3 GB: runs with part of it in system RAM, slower | flux-2-klein-9b-Q3_K_M.gguf (4.8 GB) |
| 8 GB | Offload only | Short by 4.3 GB: runs with part of it in system RAM, slower | flux-2-klein-9b-Q3_K_M.gguf (4.8 GB) |
| 10 GB | Offload only | Short by 2.3 GB: runs with part of it in system RAM, slower | flux-2-klein-9b-Q5_K_M.gguf (7.0 GB) |
| 12 GB | Offload only | Short by 0.3 GB: runs with part of it in system RAM, slower | flux-2-klein-9b-fp8.safetensors (9.4 GB) |
| 16 GB | Runs well | Fits in VRAM, 3.7 GB to spare | flux-2-klein-9b-fp8.safetensors (9.4 GB) |
| 20 GB | Runs well | Fits in VRAM, 7.7 GB to spare | flux-2-klein-9b-fp8.safetensors (9.4 GB) |
| 24 GB | Runs well | Fits in VRAM, 11.7 GB to spare | flux-2-klein-9b.safetensors (18.2 GB) |
| 32 GB | Runs well | Fits in VRAM, 19.7 GB to spare | flux-2-klein-9b.safetensors (18.2 GB) |
| 48 GB | Runs well | Fits in VRAM, 35.7 GB to spare | flux-2-klein-9b.safetensors (18.2 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 | 8.5 s per image | 1024x1024 | 4 | 13.5 GB | measured by me, 2026-10-01 |
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 | flux-2-klein-9b-Q8_0.gguf | 10.0 GB | models/unet |
| Text encoder | qwen_3_8b_fp8mixed.safetensors | 8.7 GB | models/text_encoders |
| VAE | flux2-vae.safetensors | 0.3 GB | models/vae |
19.0 GB in total. Smaller text-encoder versions and other options are on the FLUX.2 klein 9B page.
Other files of FLUX.2 klein 9B
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| flux-2-klein-9b.safetensors | 16-bit | 18.2 GB | 20.5 GB |
| flux-2-klein-9b-Q8_0.gguf | Q8_0 | 10.0 GB | 12.3 GB |
| flux-2-klein-9b-fp8.safetensors | FP8 | 9.4 GB | 11.7 GB |
| flux-2-klein-9b-Q6_K.gguf | Q6_K | 7.9 GB | 10.2 GB |
| flux-2-klein-9b-Q5_K_M.gguf | Q5_K_M | 7.0 GB | 9.3 GB |
| flux-2-klein-9b-Q4_K_M.gguf | Q4_K_M | 5.9 GB | 8.2 GB |
| flux-2-klein-9b-Q3_K_M.gguf | Q3_K_M | 4.8 GB | 7.1 GB |
| flux-2-klein-9b-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.2 klein 9B — GGUF Q8_0 — 8.5 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).