Check my GPU →

Boogu-Image (Turbo) on 10 GB of VRAM

Not entirely. Even Q5_1 is 1.2 GB over 10 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.

Image model · 10.29BAny 10 GB GPUData 2026-10-01
Offload
Not entirely in VRAM, but it can still run.

Nothing fits entirely, but Q5_1 (8.6 GB) overflows by only about 1.2 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.

Best fileQ5_1
File size8.6 GB
VRAM needed~11.2 GB
System RAM32 GB+
Memory map · 10 GB GPU11.2 GB needed · 1.2 GB over 10 GB
06 GB11 GB
Weights Q5_1 · 8.6 GBWorking memory · 1.8 GBReserve · 0.8 GBSpills to system RAM · 1.2 GB
calculated How this is counted.

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

6 GB Offload only8 GB Offload only12 GB Runs16 GB Runs well20 GB Runs well24 GB Runs well32 GB Runs well

02Every file, on 10 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
20.6 GB23.2 GB13.2 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · realrebelai
11.6 GB14.2 GB4.2 GB too bigpractically identical to the originalHugging Face →
FP8
SAFETENSORS · Comfy-Org
10.3 GB12.9 GB2.9 GB too bigpractically identical to the originalHugging Face →
INT8
SAFETENSORS · Comfy-Org
11.4 GB14.0 GB4.0 GB too bigpractically identical to the originalHugging Face →
Q5_1 ←
GGUF · realrebelai
8.6 GB11.2 GBspills 1.2 GBclose; small differences in fine detailHugging Face →
Q4_1
GGUF · realrebelai
7.4 GB10.0 GBspills 0.0 GBgood; some loss in fine detail and textHugging 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

PartFileFolderSize
Modelboogu-turbo-dit-Q5_1.gguf
Q5_1 · realrebelai/Boogu-Image-Turbo_GGUFs
models/unet8.6 GBDownload →
Text encoderqwen3vl_8b_fp8_scaled.safetensors
Qwen3-VL 8B FP8 · Comfy-Org/Boogu-Image
models/text_encoders10.6 GBDownload →
VAEflux1_vae_bf16.safetensors
FLUX.1 VAE BF16 · Comfy-Org/Boogu-Image
models/vae0.2 GBDownload →
Total download · keep about the same free on disk19.4 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 10 GB on its own. Sizes: FP8 10.6 GB, NVFP4 6.3 GB. Why the encoder does not count against VRAM →