Check my GPU →

FLUX.2 [dev] on 10 GB of VRAM

Not realistically: the smallest FLUX.2 dev file still needs about 16 GB. The 32B second-generation FLUX. Very capable and very heavy: even 4-bit files are around 20 GB, and the text encoder is a 24B language model.

Image model · 32BAny 10 GB GPUData 2026-10-01
No
No, not realistically.

Even the smallest file (Q2_K, 12.9 GB) needs about 16.2 GB, far beyond 10 GB. It may start with heavy offloading, but this is not a realistic everyday setup. Pick a smaller model or a GPU with more memory.

Best fileQ2_K
File size12.9 GB
VRAM needed~16.2 GB
System RAM48 GB+
Memory map · 10 GB GPU16.2 GB needed · 6.2 GB over 10 GB
08 GB16 GB
Weights Q2_K · 12.9 GBWorking memory · 2.5 GBReserve · 0.8 GBSpills to system RAM · 6.2 GB
calculated How this is counted.

Also try the FP8 file (35.5 GB) on NVIDIA GPUs. 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 →

01Other amounts of VRAM

6 GB Not practical8 GB Not practical12 GB Offload only16 GB Offload only20 GB Tight24 GB Runs32 GB Runs

02Every file, on 10 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · black-forest-labs
64.4 GB67.7 GB57.7 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · city96
35.0 GB38.3 GB28.3 GB too bigpractically identical to the originalHugging Face →
FP8
SAFETENSORS · Comfy-Org
35.5 GB38.8 GB28.8 GB too bigpractically identical to the originalHugging Face →
Q6_K
GGUF · city96
27.4 GB30.7 GB20.7 GB too bigvery close to the originalHugging Face →
Q5_K_M
GGUF · city96
24.1 GB27.4 GB17.4 GB too bigclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · city96
20.1 GB23.4 GB13.4 GB too biggood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · city96
16.0 GB19.3 GB9.3 GB too bignoticeable loss of detailHugging Face →
Q2_K ←
GGUF · city96
12.9 GB16.2 GB6.2 GB too bigheavy loss; a last resortHugging Face →

“Needed” adds 2.5 GB of working memory for FLUX.2 dev and a 0.8 GB reserve. Sizes 2026-10-01.

03What to download

PartFileFolderSize
Modelflux2-dev-Q2_K.gguf
Q2_K · city96/FLUX.2-dev-gguf
models/unet12.9 GBDownload →
Text encodermistral_3_small_flux2_fp8.safetensors
Mistral 3 Small FP8 · Comfy-Org/flux2-dev
models/text_encoders18.0 GBDownload →
VAEflux2-vae.safetensors
FLUX.2 VAE · Comfy-Org/flux2-dev
models/vae0.3 GBDownload →
Total download · keep about the same free on disk31.2 GB

Alternatives: Mistral 3 Small BF16 (35.6 GB). Sizes from Hugging Face, 2026-10-01.

System RAM: 48 GB or more. These files take about 31.2 GB of RAM while loaded, 37.2 GB with Windows and ComfyUI. What happens with less. calculated

04The text encoder

At 18.0 GB even the smallest Mistral Small 3 (24B) file is too big for 10 GB, so it runs from system RAM. That slows down reading the prompt, not the picture. Sizes: 16-bit 35.6 GB, FP8 18.0 GB. Why the encoder does not count against VRAM →