Can the RTX 3080 10 GB run FLUX.2 [klein] 9B?
Not at full quality. The 16-bit and 8-bit files are too big for the RTX 3080 10 GB; the largest that fits is Q5_K_M (7.0 GB).
Q5_K_M (7.0 GB) fits with only 0.7 GB to spare (about 9.3 GB of 10 GB). Quality: close; small differences in fine detail. For better quality, Q6_K (7.9 GB) also runs, with about 0.2 GB spilling into system RAM - a little slower, still practical.
Also try the FP8 file (9.4 GB) on this GPU. 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 →
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux-2-klein-9b-Q5_K_M.gguf Q5_K_M · unsloth/FLUX.2-klein-9B-GGUF | models/unet | 7.0 GB | Download → |
| Text encoder | qwen_3_8b_fp8mixed.safetensors Qwen3 8B FP8 · Comfy-Org/flux2-klein-9B | models/text_encoders | 8.7 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 | 16.0 GB | |||
Alternatives: Qwen3 8B BF16 (16.4 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: GGUF Q8_0 workflow (.json). Drag the file into ComfyUI. All workflows →
02Every FLUX.2 klein 9B file on 10 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 18.2 GB | 20.5 GB | 10.5 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · unsloth | 10.0 GB | 12.3 GB | 2.3 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · black-forest-labs | 9.4 GB | 11.7 GB | spills 1.7 GB | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 7.9 GB | 10.2 GB | spills 0.2 GB | very close to the original | Hugging Face → |
| Q5_K_M ← GGUF · unsloth | 7.0 GB | 9.3 GB | fits · 0.7 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 5.9 GB | 8.2 GB | fits · 1.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 4.8 GB | 7.1 GB | fits · 2.9 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 4.0 GB | 6.3 GB | fits · 3.7 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1.5 GB of working memory for FLUX.2 klein 9B 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 9B on a RTX 3080 10 GB, send your time per image and peak VRAM and it will appear here, credited.
04With more VRAM
With 12 GB you could run FLUX.2 klein 9B at 8-bit or better (FP8, 9.4 GB) with no offloading: for example on the RTX 5070 12 GB, RTX 4070 Super 12 GB, RTX 4070 12 GB.
What changes from the RTX 3080 10 GB to the RTX 3090 24 GB → · What changes from the RTX 3080 10 GB to the RTX 5070 Ti 16 GB →
05About the RTX 3080 10 GB
The RTX 3080 10 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.
10 GB GDDR6X · 320-bit · 760 GB/s · Ampere. Everything that runs on it →
06Questions
How much VRAM does FLUX.2 klein 9B need?
Around 6.3 GB with the smallest file (Q2_K) and 11.7 GB with an 8-bit file (FP8). The full 16-bit file needs about 20.5 GB.
Which FLUX.2 klein 9B file should I download for the RTX 3080 10 GB?
Q5_K_M (7.0 GB) from unsloth/FLUX.2-klein-9B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for FLUX.2 klein 9B on the RTX 3080 10 GB?
Q8_0 (10.0 GB). The RTX 3080 10 GB has no FP8 maths, so FP8 (9.4 GB) only saves memory and is a step further from the original.
How much do I need to download for FLUX.2 klein 9B on the RTX 3080 10 GB?
16.0 GB: flux-2-klein-9b-Q5_K_M.gguf, qwen_3_8b_fp8mixed.safetensors, flux2-vae.safetensors.