Can the RTX 3060 Ti 8 GB run FLUX.2 [klein] 4B?
Yes, but only just: Q8_0 leaves 1.9 GB free on the RTX 3060 Ti 8 GB.
Q8_0 (4.3 GB) fits with only 1.9 GB to spare (about 6.1 GB of 8 GB).
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux-2-klein-4b-Q8_0.gguf Q8_0 · unsloth/FLUX.2-klein-4B-GGUF | models/unet | 4.3 GB | Download → |
| Text encoder | qwen_3_4b_fp8_mixed.safetensors Qwen3 4B FP8 · Comfy-Org/z_image_turbo | models/text_encoders | 5.6 GB | Download → |
| VAE | flux2-vae.safetensors FLUX.2 VAE · Comfy-Org/flux2-dev | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 10.3 GB | |||
Alternatives: Qwen3 4B BF16 (8.0 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: FP8 workflow (.json). Drag the file into ComfyUI. All workflows →
02Every FLUX.2 klein 4B file on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 7.8 GB | 9.6 GB | spills 1.6 GB | the original weights | Hugging Face → |
| Q8_0 ← GGUF · unsloth | 4.3 GB | 6.1 GB | fits · 1.9 GB spare | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · black-forest-labs | 4.1 GB | 5.9 GB | fits · 2.1 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 3.4 GB | 5.2 GB | fits · 2.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 3.1 GB | 4.9 GB | fits · 3.1 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 2.6 GB | 4.4 GB | fits · 3.6 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 2.1 GB | 3.9 GB | fits · 4.1 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 1.8 GB | 3.6 GB | fits · 4.4 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1 GB of working memory for FLUX.2 klein 4B 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 FLUX.2 klein 4B 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 FLUX.2 klein 4B need?
Around 3.6 GB with the smallest file (Q2_K) and 5.9 GB with an 8-bit file (FP8). The full 16-bit file needs about 9.6 GB.
Which FLUX.2 klein 4B file should I download for the RTX 3060 Ti 8 GB?
Q8_0 (4.3 GB) from unsloth/FLUX.2-klein-4B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for FLUX.2 klein 4B on the RTX 3060 Ti 8 GB?
Q8_0 (4.3 GB). The RTX 3060 Ti 8 GB has no FP8 maths, so FP8 (4.1 GB) only saves memory and is a step further from the original.
How much do I need to download for FLUX.2 klein 4B on the RTX 3060 Ti 8 GB?
10.3 GB: flux-2-klein-4b-Q8_0.gguf, qwen_3_4b_fp8_mixed.safetensors, flux2-vae.safetensors.