Boogu-Image (Turbo) on 6 GB of VRAM
The smallest sensible file, Q4_1 (7.4 GB), needs about 10.0 GB — 4.0 GB more than 6 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.
Worth trying on NVIDIA GPUs: with an up-to-date ComfyUI, Dynamic VRAM (on by default for NVIDIA since March 2026) streams whatever does not fit from system RAM, and ComfyUI's own start-up message recommends native FP8/INT8 files over GGUF, saying they “will be faster even if they are larger than your memory”. So before settling for a heavily compressed GGUF, try the native FP8 file (10.3 GB). The file recommended above is the best one that fits entirely — the safe choice on older ComfyUI versions, AMD and Intel. Comfy blog: Dynamic VRAM →
01What 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 read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.
System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 18.2 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 24.2 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every file, on 6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 20.6 GB | 23.2 GB | 17.2 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · realrebelai | 11.6 GB | 14.2 GB | 8.2 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 10.3 GB | 12.9 GB | 6.9 GB too big | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 11.4 GB | 14.0 GB | 8.0 GB too big | practically identical to the original | Hugging Face → |
| Q5_1 GGUF · realrebelai | 8.6 GB | 11.2 GB | 5.2 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_1 ← GGUF · realrebelai | 7.4 GB | 10.0 GB | 4.0 GB too big | good; some loss in fine detail and text | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1.8 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
Qwen3-VL 8B: 10.6 GB as FP8, 6.3 GB as NVFP4. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 6 GB the encoder itself is too big for VRAM, so let it run from system RAM: slower prompt encoding, same images.