Can the RTX 5070 12 GB run FLUX.1 Kontext [dev]?
Not at full quality. The 16-bit and 8-bit files are too big for the RTX 5070 12 GB; the largest that fits is Q5_K_M (8.4 GB).
Q5_K_M (8.4 GB) fits with only 1.0 GB to spare (about 11.0 GB of 12 GB). Quality: close; small differences in fine detail. For better quality, Q6_K (9.8 GB) also runs, with about 0.4 GB spilling into system RAM - a little slower, still practical.
Also try the FP8 file (11.9 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 →
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux1-kontext-dev-Q5_K_M.gguf Q5_K_M · QuantStack/FLUX.1-Kontext-dev-GGUF | models/unet | 8.4 GB | Download → |
| Text encoder | t5xxl_fp8_e4m3fn.safetensors T5-XXL FP8 · comfyanonymous/flux_text_encoders | models/text_encoders | 4.9 GB | Download → |
| Text encoder | clip_l.safetensors CLIP-L · comfyanonymous/flux_text_encoders | models/text_encoders | 0.2 GB | Download → |
| VAE | ae.safetensors FLUX.1 VAE (ae) · Comfy-Org/Lumina_Image_2.0_Repackaged | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 13.9 GB | |||
Alternatives: T5-XXL FP16 (9.8 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: FP8 workflow (.json) · GGUF Q8_0 workflow (.json). Drag the file into ComfyUI. All workflows →
02Every FLUX.1 Kontext file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 23.8 GB | 26.4 GB | 14.4 GB too big | the original weights | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 11.9 GB | 14.5 GB | 2.5 GB too big | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · QuantStack | 12.7 GB | 15.3 GB | 3.3 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 9.8 GB | 12.4 GB | spills 0.4 GB | very close to the original | Hugging Face → |
| Q5_K_M ← GGUF · QuantStack | 8.4 GB | 11.0 GB | fits · 1.0 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 6.9 GB | 9.5 GB | fits · 2.5 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 5.4 GB | 8.0 GB | fits · 4.0 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 4.0 GB | 6.6 GB | fits · 5.4 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1.8 GB of working memory for FLUX.1 Kontext and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run FLUX.1 Kontext on a RTX 5070 12 GB, send your time per image and peak VRAM and it will appear here, credited.
04With more VRAM
With 16 GB you could run FLUX.1 Kontext at 8-bit or better (FP8, 11.9 GB) with no offloading: for example on the RTX 5080 16 GB, RTX 5070 Ti 16 GB, RTX 5060 Ti 16 GB.
What changes from the RTX 5070 12 GB to the RTX 5070 Ti 16 GB →
05About the RTX 5070 12 GB
The RTX 5070 12 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.
12 GB GDDR7 · 192-bit · 672 GB/s · Blackwell. Everything that runs on it →
06Questions
How much VRAM does FLUX.1 Kontext need?
Around 6.6 GB with the smallest file (Q2_K) and 14.5 GB with an 8-bit file (FP8). The full 16-bit file needs about 26.4 GB.
Which FLUX.1 Kontext file should I download for the RTX 5070 12 GB?
Q5_K_M (8.4 GB) from QuantStack/FLUX.1-Kontext-dev-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for FLUX.1 Kontext on the RTX 5070 12 GB?
FP8 (11.9 GB): the RTX 5070 12 GB computes it natively, while Q8_0 (12.7 GB) is unpacked on the fly.
How much do I need to download for FLUX.1 Kontext on the RTX 5070 12 GB?
13.9 GB: flux1-kontext-dev-Q5_K_M.gguf, t5xxl_fp8_e4m3fn.safetensors, clip_l.safetensors, ae.safetensors.