Can the RTX 5070 Ti 16 GB run FLUX.2 [dev]?
Not entirely. Even Q2_K is 0.2 GB over 16 GB, so ComfyUI keeps part of it in system RAM.
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.
Also try the FP8 file (35.5 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 →
01With more VRAM
With 48 GB you could run FLUX.2 dev at 8-bit or better (FP8, 35.5 GB) with no offloading.
What changes from the RTX 5070 Ti 16 GB to the RTX 5090 32 GB →
02Every FLUX.2 dev file on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 64.4 GB | 67.7 GB | 51.7 GB too big | the original weights | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 35.5 GB | 38.8 GB | 22.8 GB too big | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · city96 | 35.0 GB | 38.3 GB | 22.3 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 27.4 GB | 30.7 GB | 14.7 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 24.1 GB | 27.4 GB | 11.4 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · city96 | 20.1 GB | 23.4 GB | 7.4 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 16.0 GB | 19.3 GB | 3.3 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K ← GGUF · city96 | 12.9 GB | 16.2 GB | spills 0.2 GB | heavy loss; a last resort | Hugging 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
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux2-dev-Q2_K.gguf Q2_K · city96/FLUX.2-dev-gguf | models/unet | 12.9 GB | Download → |
| Text encoder | mistral_3_small_flux2_fp8.safetensors Mistral 3 Small FP8 · Comfy-Org/flux2-dev | models/text_encoders | 18.0 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 | 31.2 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 →
05Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run FLUX.2 dev on a RTX 5070 Ti 16 GB, send your time per image and peak VRAM and it will appear here, credited.
06About the RTX 5070 Ti 16 GB
The RTX 5070 Ti 16 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.
16 GB GDDR7 · 256-bit · 896 GB/s · Blackwell. Everything that runs on it →
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). The full 16-bit file needs about 67.7 GB.
Which FLUX.2 dev file should I download for the RTX 5070 Ti 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.
FP8 or Q8_0 for FLUX.2 dev on the RTX 5070 Ti 16 GB?
FP8 (35.5 GB): the RTX 5070 Ti 16 GB computes it natively, while Q8_0 (35.0 GB) is unpacked on the fly.
How much do I need to download for FLUX.2 dev on the RTX 5070 Ti 16 GB?
31.2 GB: flux2-dev-Q2_K.gguf, mistral_3_small_flux2_fp8.safetensors, flux2-vae.safetensors.