Boogu-Image (Turbo) VRAM requirements
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.
TypeImage
Parameters10.29B
Fits entirely from11 GB
8-bit or better from13 GB
01The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 20.6 GB | 23.2 GB | 24 GB | the original weights | Comfy-Org/Boogu-Image → |
| Q8_0 | 11.6 GB | 14.2 GB | 15 GB | practically identical to the original | realrebelai/Boogu-Image-Turbo_GGUFs → |
| FP8 | 10.3 GB | 12.9 GB | 13 GB | practically identical to the original | Comfy-Org/Boogu-Image → |
| INT8 | 11.4 GB | 14.0 GB | 14 GB | practically identical to the original | Comfy-Org/Boogu-Image → |
| Q5_1 | 8.6 GB | 11.2 GB | 12 GB | close; small differences in fine detail | realrebelai/Boogu-Image-Turbo_GGUFs → |
| Q4_1 | 7.4 GB | 10.0 GB | 11 GB | good; some loss in fine detail and text | realrebelai/Boogu-Image-Turbo_GGUFs → |
“Needed” = file + 1.8 GB working memory + 0.8 GB system reserve.
02By amount of VRAM
03Best GPU for Boogu-Image
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for Boogu-Image → Planning bigger images or longer clips? Open the calculator →
04By graphics card
| GPU | VRAM | Verdict | Best file | Needed |
|---|---|---|---|---|
| Desktop graphics cards | ||||
| RTX 2060 6 GB | 6 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3050 6 GB | 6 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 2070 Super 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 2080 Super 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3050 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3060 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3060 Ti 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3070 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3070 Ti 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 4060 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 4060 Ti 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 5050 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 5060 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 5060 Ti 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RX 7600 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RX 9050 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RX 9060 XT 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| Arc B570 10 GB | 10 GB | Offload only | Q5_1 | 11.2 GB |
| RTX 3080 10 GB | 10 GB | Offload only | Q5_1 | 11.2 GB |
| RTX 2080 Ti 11 GB | 11 GB | Runs | Q4_1 | 10.0 GB |
| Arc B580 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 2060 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 3060 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 3080 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 3080 Ti 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 4070 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 4070 Super 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 4070 Ti 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 5070 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RX 7700 XT 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RX 9070 GRE 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| Arc A770 16 GB | 16 GB | Runs well | Q8_0 | 14.2 GB |
| RTX 4060 Ti 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RTX 4080 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RTX 4080 Super 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RTX 5060 Ti 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RTX 5070 Ti 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RTX 5080 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RX 7600 XT 16 GB | 16 GB | Runs well | Q8_0 | 14.2 GB |
| RX 7800 XT 16 GB | 16 GB | Runs well | Q8_0 | 14.2 GB |
| RX 7900 GRE 16 GB | 16 GB | Runs well | Q8_0 | 14.2 GB |
| RX 9060 XT 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RX 9070 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RX 9070 XT 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RX 7900 XT 20 GB | 20 GB | Runs well | Q8_0 | 14.2 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | 16-bit | 23.2 GB |
| RTX 3090 24 GB | 24 GB | Runs well | 16-bit | 23.2 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | 16-bit | 23.2 GB |
| RTX 4090 24 GB | 24 GB | Runs well | 16-bit | 23.2 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | 16-bit | 23.2 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | 16-bit | 23.2 GB |
| RTX 5090 32 GB | 32 GB | Runs well | 16-bit | 23.2 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RX 7600M 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RX 7600M XT 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RX 7600S 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RX 7700S 8 GB | 8 GB | Offload only | Q4_1 | 10.0 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RX 7800M 12 GB | 12 GB | Runs | Q5_1 | 11.2 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Runs well | Q8_0 | 14.2 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Runs well | Q8_0 | 14.2 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Runs well | FP8 | 12.9 GB |
| RX 7900M 16 GB | 16 GB | Runs well | Q8_0 | 14.2 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | 16-bit | 23.2 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 23.2 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 23.2 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Runs | Q5_1 | 11.2 GB |
| Mac 18 GB | 14.4 GB | Runs well | Q8_0 | 14.2 GB |
| Mac 24 GB | 19.6 GB | Runs well | Q8_0 | 14.2 GB |
| Mac 32 GB | 26.8 GB | Runs well | 16-bit | 23.2 GB |
| Mac 36 GB | 30.2 GB | Runs well | 16-bit | 23.2 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 23.2 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 23.2 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 23.2 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 23.2 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 23.2 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 23.2 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 23.2 GB |
05Text encoder, VAE and other files
| File | Folder | Size | When | |
|---|---|---|---|---|
| Qwen3-VL 8B FP8 qwen3vl_8b_fp8_scaled.safetensors | models/text_encoders | 10.6 GB | text encoder · smaller, recommended | Download → |
| FLUX.1 VAE BF16 flux1_vae_bf16.safetensors | models/vae | 0.2 GB | required | Download → |
The files the official ComfyUI workflows load next to the model. Sizes read from Hugging Face (2026-10-01).
06Where the files go in ComfyUI
| File | Folder | Loader node |
|---|---|---|
| Diffusion model (.safetensors: 16-bit, FP8, INT8) | ComfyUI/models/diffusion_models | Load Diffusion Model |
| GGUF file (.gguf) | ComfyUI/models/unet | Unet Loader (GGUF) - from the ComfyUI-GGUF node pack |
| Text encoder | ComfyUI/models/text_encoders | Load CLIP / DualCLIPLoader (or the GGUF versions) |
| VAE | ComfyUI/models/vae | Load VAE |
07Measured and reported results
No measured results yet. Send yours.
08Training a LoRA for Boogu-Image
No trainer documentation with a VRAM figure for this model was found yet. What the trainers say for other models →
09Every file tracked for Boogu-Image
| File | Type | Size | Repo |
|---|---|---|---|
| boogu_image_turbo_hotfix_bf16.safetensors (turbo-hotfix) | BF16 | 20.59 GB | Comfy-Org/Boogu-Image → |
| boogu_image_base_bf16.safetensors (base) | BF16 | 20.59 GB | Comfy-Org/Boogu-Image → |
| boogu_image_edit_turbo_bf16.safetensors (edit-turbo) | BF16 | 20.59 GB | Comfy-Org/Boogu-Image → |
| boogu_image_edit_turbo_hotfix_1k_20260708_bf16.safetensors (edit-turbo-hotfix) | BF16 | 20.59 GB | Comfy-Org/Boogu-Image → |
| boogu_image_turbo_bf16.safetensors (turbo) | BF16 | 20.59 GB | Comfy-Org/Boogu-Image → |
| boogu_image_edit_bf16.safetensors (edit) | BF16 | 20.59 GB | Comfy-Org/Boogu-Image → |
| boogu_image_turbo_hotfix_int8_convrot.safetensors (turbo-hotfix) | INT8 | 11.37 GB | Comfy-Org/Boogu-Image → |
| boogu_image_edit_int8_convrot.safetensors (edit) | INT8 | 11.37 GB | Comfy-Org/Boogu-Image → |
| boogu_image_edit_turbo_int8_convrot.safetensors (edit-turbo) | INT8 | 11.37 GB | Comfy-Org/Boogu-Image → |
| boogu_image_edit_turbo_hotfix_1k_20260708_int8_convrot.safetensors (edit-turbo-hotfix) | INT8 | 10.33 GB | Comfy-Org/Boogu-Image → ~1 GB smaller than the other int8_convrot files; confirmed on two fetches |
| boogu_image_turbo_fp8_scaled.safetensors (turbo) | FP8 | 10.31 GB | Comfy-Org/Boogu-Image → |
| boogu_image_base_fp8_scaled.safetensors (base) | FP8 | 10.31 GB | Comfy-Org/Boogu-Image → |
| boogu_image_edit_fp8_scaled.safetensors (edit) | FP8 | 10.31 GB | Comfy-Org/Boogu-Image → |
| boogu_image_turbo_nvfp4.safetensors (turbo) | NVFP4 | 5.83 GB | Comfy-Org/Boogu-Image → |
| boogu_image_turbo_hotfix_nvfp4.safetensors (turbo-hotfix) | NVFP4 | 5.83 GB | Comfy-Org/Boogu-Image → |
| boogu_image_base_nvfp4.safetensors (base) | NVFP4 | 5.83 GB | Comfy-Org/Boogu-Image → |
| boogu_image_edit_nvfp4.safetensors (edit) | NVFP4 | 5.83 GB | Comfy-Org/Boogu-Image → |
| boogu-turbo-dit-Q8_0.gguf (turbo) | Q8_0 | 11.64 GB | realrebelai/Boogu-Image-Turbo_GGUFs → |
| Boogu-Turbo-V2_dit-Q8_0.gguf (turbo-v2) | Q8_0 | 11.59 GB | realrebelai/Boogu-Image-Turbo_GGUFs → repo README: 'V2 GGUFs are LIVE' (likely the turbo hotfix; not stated) |
| boogu-turbo-dit-Q5_1.gguf (turbo) | Q5_1 | 8.64 GB | realrebelai/Boogu-Image-Turbo_GGUFs → |
| Boogu-Turbo-V2_dit-Q5_1.gguf (turbo-v2) | Q5_1 | 8.59 GB | realrebelai/Boogu-Image-Turbo_GGUFs → repo README: 'V2 GGUFs are LIVE' (likely the turbo hotfix; not stated) |
| boogu-turbo-dit-Q5_0.gguf (turbo) | Q5_0 | 8.04 GB | realrebelai/Boogu-Image-Turbo_GGUFs → |
| Boogu-Turbo-V2_dit-Q5_0.gguf (turbo-v2) | Q5_0 | 7.99 GB | realrebelai/Boogu-Image-Turbo_GGUFs → repo README: 'V2 GGUFs are LIVE' (likely the turbo hotfix; not stated) |
| boogu-turbo-dit-Q4_1.gguf (turbo) | Q4_1 | 7.44 GB | realrebelai/Boogu-Image-Turbo_GGUFs → |
| Boogu-Turbo-V2_dit-Q4_1.gguf (turbo-v2) | Q4_1 | 7.38 GB | realrebelai/Boogu-Image-Turbo_GGUFs → repo README: 'V2 GGUFs are LIVE' (likely the turbo hotfix; not stated) |
| boogu-turbo-dit-Q4_0.gguf (turbo) | Q4_0 | 6.84 GB | realrebelai/Boogu-Image-Turbo_GGUFs → |
| Boogu-Turbo-V2_dit-Q4_0.gguf (turbo-v2) | Q4_0 | 6.78 GB | realrebelai/Boogu-Image-Turbo_GGUFs → repo README: 'V2 GGUFs are LIVE' (likely the turbo hotfix; not stated) |
10.3B unified generation/editing DiT (HF API 10.29B BF16) from the Boogu project. Turbo = 4-step distilled (1K); Base 25-50 steps (1K-2K); Edit and Edit-Turbo are separate checkpoints. Hotfix turbo released 2026-06-25, edit-turbo hotfix 2026-07-08. VAE: flux1_vae_bf16 (167664710). Native ComfyUI support (PR #14523, docs.comfy.org workflow); official ComfyUI-Boogu custom nodes also exist. GGUF via ComfyUI-GGUF.