Can the RTX 3060 Ti 8 GB run Lumina Image 2.0?
Yes, but only just: 16-bit leaves 1.0 GB free on the RTX 3060 Ti 8 GB.
16-bit (5.2 GB) fits with only 1.0 GB to spare (about 7.0 GB of 8 GB).
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | lumina_2_model_bf16.safetensors 16-bit · Comfy-Org/Lumina_Image_2.0_Repackaged | models/diffusion_models | 5.2 GB | Download → |
| Text encoder | gemma_2_2b_fp16.safetensors Gemma 2 2B FP16 · Comfy-Org/Lumina_Image_2.0_Repackaged | models/text_encoders | 5.2 GB | Download → |
| VAE | ae.safetensors FLUX.1 VAE (ae) · Comfy-Org/Lumina_Image_2.0_Repackaged | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 10.8 GB | |||
Sizes from Hugging Face, 2026-10-01.
02Every Lumina 2.0 file on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · Comfy-Org | 5.2 GB | 7.0 GB | fits · 1.0 GB spare | the original weights | Hugging Face → |
| Q8_0 GGUF · calcuis | 2.8 GB | 4.6 GB | fits · 3.4 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · calcuis | 2.1 GB | 3.9 GB | fits · 4.1 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · calcuis | 1.8 GB | 3.6 GB | fits · 4.4 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · calcuis | 1.5 GB | 3.3 GB | fits · 4.7 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · calcuis | 1.1 GB | 2.9 GB | fits · 5.1 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · calcuis | 1.1 GB | 2.9 GB | fits · 5.1 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1 GB of working memory for Lumina 2.0 and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Lumina 2.0 on a RTX 3060 Ti 8 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 3060 Ti 8 GB
The RTX 3060 Ti 8 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain - Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.
8 GB GDDR6 · 256-bit · 448 GB/s · Ampere. Everything that runs on it →
05Questions
How much VRAM does Lumina 2.0 need?
Around 2.9 GB with the smallest file (Q2_K) and 4.6 GB with an 8-bit file (Q8_0). The full 16-bit file needs about 7.0 GB.
Which Lumina 2.0 file should I download for the RTX 3060 Ti 8 GB?
16-bit (5.2 GB) from Comfy-Org/Lumina_Image_2.0_Repackaged.
How much do I need to download for Lumina 2.0 on the RTX 3060 Ti 8 GB?
10.8 GB: lumina_2_model_bf16.safetensors, gemma_2_2b_fp16.safetensors, ae.safetensors.