Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Can the RTX 3060 12 GB run FLUX.1 [dev]?

Image model · 12B12 GB GDDR6 · 192-bit · 360 GB/s · AmpereData 2026-09-25
Runs
Yes, with a compressed file.

Download Q5_K_S (8.3 GB). With the model's working memory it needs about 10.6 GB, leaving 1.4 GB spare on 12 GB. Quality: close; small differences in fine detail. For better quality, Q6_K (9.9 GB) also runs, with about 0.2 GB spilling into system RAM — a little slower, still practical.

Best fileQ5_K_S
File size8.3 GB
VRAM needed~10.6 GB
System RAM32 GB+
Memory map · RTX 3060 12 GB10.6 GB / 12 GB
06 GB12 GB
Weights Q5_K_S · 8.3 GBWorking memory · 1.5 GBReserve · 0.8 GBFree · 1.4 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

Worth trying on this GPU: with an up-to-date ComfyUI, Dynamic VRAM (on by default for NVIDIA since March 2026) streams whatever does not fit from system RAM, and ComfyUI's own start-up message recommends native FP8/INT8 files over GGUF, saying they “will be faster even if they are larger than your memory”. So before settling for a heavily compressed GGUF, try the native FP8 file (11.9 GB). The file recommended above is the best one that fits entirely — the safe choice on older ComfyUI versions, AMD and Intel. Comfy blog: Dynamic VRAM →

01What to download

PartFileFolderSize
Modelflux1-dev-Q5_K_S.gguf
Q5_K_S · city96/FLUX.1-dev-gguf
models/unet8.3 GBDownload →
Text encodert5xxl_fp8_e4m3fn.safetensors
T5-XXL FP8 · comfyanonymous/flux_text_encoders
models/text_encoders4.9 GBDownload →
Text encoderclip_l.safetensors
CLIP-L · comfyanonymous/flux_text_encoders
models/text_encoders0.2 GBDownload →
VAEae.safetensors
FLUX.1 VAE (ae) · Comfy-Org/Lumina_Image_2.0_Repackaged
models/vae0.3 GBDownload →
Total download · keep about the same free on disk13.8 GB

Alternatives: T5-XXL FP16 (9.8 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.

System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 13.8 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 19.8 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every FLUX.1 dev file on 12 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · black-forest-labs
23.8 GB26.1 GB14.1 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · city96
12.7 GB15.0 GB3.0 GB too bigpractically identical to the originalHugging Face →
FP8
SAFETENSORS · Kijai
11.9 GB14.2 GB2.2 GB too bigpractically identical to the originalHugging Face →
Q6_K
GGUF · city96
9.9 GB12.2 GBspills 0.2 GBvery close to the originalHugging Face →
Q5_K_S ←
GGUF · city96
8.3 GB10.6 GBfits · 1.4 GB spareclose; small differences in fine detailHugging Face →
Q4_K_S
GGUF · city96
6.8 GB9.1 GBfits · 2.9 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_S
GGUF · city96
5.2 GB7.5 GBfits · 4.5 GB sparenoticeable loss of detailHugging Face →
Q2_K
GGUF · city96
4.0 GB6.3 GBfits · 5.7 GB spareheavy loss; a last resortHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1.5 GB working memory for this model + 0.8 GB kept free for the system.

03The text encoder

T5-XXL: 9.8 GB as 16-bit, 4.9 GB as FP8, 2.9 GB as GGUF Q4_K_M (plus CLIP-L (0.25 GB)). ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 12 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

04About this GPU

The RTX 3060 12 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.

RTX 3060 12 GB: 12 GB GDDR6 · 192-bit · 360 GB/s · Ampere. Everything that runs on the RTX 3060 12 GB →

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run FLUX.1 dev on a RTX 3060 12 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

How much VRAM does FLUX.1 dev need?

Around 6.3 GB with the smallest file (Q2_K) and 14.2 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 26.1 GB.

Which FLUX.1 dev file should I download for the RTX 3060 12 GB?

Q5_K_S (8.3 GB) from city96/FLUX.1-dev-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.

Is FP8 faster than GGUF on the RTX 3060 12 GB?

No. This GPU has no FP8 compute, so ComfyUI converts FP8 weights back before the maths. FP8 only saves memory here; Q8_0 GGUF is the closer-to-original 8-bit pick.

How much do I need to download for FLUX.1 dev on the RTX 3060 12 GB?

About 13.8 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 12 GB card, 32 GB of system RAM or more is recommended.