Check my GPU →

FLUX.2 [dev] on 16 GB of VRAM

Not entirely. Even Q2_K is 0.2 GB over 16 GB, so ComfyUI keeps part of it in system RAM. 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 16 GB GPUData 2026-10-01
Offload
Not entirely in VRAM, but it can still run.

Nothing fits entirely, but Q2_K (12.9 GB) overflows by only about 0.2 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.

Best fileQ2_K
File size12.9 GB
VRAM needed~16.2 GB
System RAM48 GB+
Memory map · 16 GB GPU16.2 GB needed · 0.2 GB over 16 GB
08 GB16 GB
Weights Q2_K · 12.9 GBWorking memory · 2.5 GBReserve · 0.8 GBSpills to system RAM · 0.2 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 practical10 GB Not practical12 GB Offload only20 GB Tight24 GB Runs32 GB Runs

02Every file, on 16 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · black-forest-labs
64.4 GB67.7 GB51.7 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · city96
35.0 GB38.3 GB22.3 GB too bigpractically identical to the originalHugging Face →
FP8
SAFETENSORS · Comfy-Org
35.5 GB38.8 GB22.8 GB too bigpractically identical to the originalHugging Face →
Q6_K
GGUF · city96
27.4 GB30.7 GB14.7 GB too bigvery close to the originalHugging Face →
Q5_K_M
GGUF · city96
24.1 GB27.4 GB11.4 GB too bigclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · city96
20.1 GB23.4 GB7.4 GB too biggood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · city96
16.0 GB19.3 GB3.3 GB too bignoticeable loss of detailHugging Face →
Q2_K ←
GGUF · city96
12.9 GB16.2 GBspills 0.2 GBheavy 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 16 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 →