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

Can the RX 9070 XT 16 GB run FLUX.2 [dev]?

Image model · 32B16 GB GDDR6 · 256-bit · 640 GB/s · RDNA 4Data 2026-09-25
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 · RX 9070 XT 16 GB16.2 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 from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What 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). 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: 48 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 31.2 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 37.2 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every FLUX.2 dev 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 →
FP8
SAFETENSORS · Comfy-Org
35.5 GB38.8 GB22.8 GB too bigpractically identical to the originalHugging Face →
Q8_0
GGUF · city96
35.0 GB38.3 GB22.3 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 →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 2.5 GB working memory for this model + 0.8 GB kept free for the system.

03The text encoder

Mistral Small 3 (24B): 35.6 GB as 16-bit, 18.0 GB as FP8. 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 16 GB the encoder itself is too big for VRAM, so let it run from system RAM: slower prompt encoding, same images.

04About this GPU

ComfyUI supports AMD GPUs on Windows officially since v0.7.0 (January 2026), through ROCm. Memory works the same as on NVIDIA, so the fit verdicts apply. Some custom nodes are NVIDIA-only. RX 9000 (RDNA 4) GPUs have FP8 hardware, and ComfyUI computes FP8 natively on them with PyTorch 2.7+ and ROCm 6.4+.

RX 9070 XT 16 GB: 16 GB GDDR6 · 256-bit · 640 GB/s · RDNA 4. Everything that runs on the RX 9070 XT 16 GB →

05What more VRAM would change

With 48 GB you could run FLUX.2 dev at 8-bit or better (FP8, 35.5 GB) with no offloading.

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run FLUX.2 dev on a RX 9070 XT 16 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

How much VRAM does FLUX.2 dev need?

Around 16.2 GB with the smallest file (Q2_K) and 38.8 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 67.7 GB.

Which FLUX.2 dev file should I download for the RX 9070 XT 16 GB?

Q2_K (12.9 GB) from city96/FLUX.2-dev-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.

Is FP8 faster than GGUF on the RX 9070 XT 16 GB?

It can be. This GPU has FP8 hardware, and ComfyUI computes FP8 natively for files made for it (Comfy-Org's fp8_scaled files), or for any FP8 file with the --fast fp8_matrix_mult option. GGUF files are unpacked on the fly, which costs some speed.

How much do I need to download for FLUX.2 dev on the RX 9070 XT 16 GB?

About 31.2 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 16 GB card, 48 GB of system RAM or more is recommended.