Boogu-Image (Turbo) on 8 GB of VRAM
Not entirely. Even Q4_1 is 2.0 GB over 8 GB, so ComfyUI keeps part of it in system RAM. A 10B model from June 2026 that generates and edits in one. Turbo needs about 4 steps; Base and the separate Edit checkpoints are the same size.
The smallest sensible file, Q4_1 (7.4 GB), needs about 10.0 GB - 2.0 GB more than 8 GB GPU 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.
Also try the FP8 file (10.3 GB) on NVIDIA GPUs. It does not fit entirely, but a current ComfyUI streams the overflow from RAM and native 8-bit files often beat a small GGUF that does fit. Dynamic VRAM →
01Other amounts of VRAM
02Every file, on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 20.6 GB | 23.2 GB | 15.2 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · realrebelai | 11.6 GB | 14.2 GB | 6.2 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 10.3 GB | 12.9 GB | 4.9 GB too big | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 11.4 GB | 14.0 GB | 6.0 GB too big | practically identical to the original | Hugging Face → |
| Q5_1 GGUF · realrebelai | 8.6 GB | 11.2 GB | 3.2 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_1 ← GGUF · realrebelai | 7.4 GB | 10.0 GB | 2.0 GB too big | good; some loss in fine detail and text | Hugging Face → |
“Needed” adds 1.8 GB of working memory for Boogu-Image and a 0.8 GB reserve. Sizes 2026-10-01.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | boogu-turbo-dit-Q4_1.gguf Q4_1 · realrebelai/Boogu-Image-Turbo_GGUFs | models/unet | 7.4 GB | Download → |
| Text encoder | qwen3vl_8b_fp8_scaled.safetensors Qwen3-VL 8B FP8 · Comfy-Org/Boogu-Image | models/text_encoders | 10.6 GB | Download → |
| VAE | flux1_vae_bf16.safetensors FLUX.1 VAE BF16 · Comfy-Org/Boogu-Image | models/vae | 0.2 GB | Download → |
| Total download · keep about the same free on disk | 18.2 GB | |||
Sizes from Hugging Face, 2026-10-01.
04The text encoder
Take the smallest Qwen3-VL 8B file (6.3 GB): it is the only one that fits in 8 GB on its own. Sizes: FP8 10.6 GB, NVFP4 6.3 GB. Why the encoder does not count against VRAM →