Can the RTX 4080 Super 16 GB run FLUX.1 Kontext [dev]?
Yes, but only just: FP8 leaves 1.5 GB free on the RTX 4080 Super 16 GB.
FP8 (11.9 GB) fits with only 1.5 GB to spare (about 14.5 GB of 16 GB).
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux1-dev-kontext_fp8_scaled.safetensors FP8 · Comfy-Org/flux1-kontext-dev_ComfyUI | models/diffusion_models | 11.9 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 | 17.4 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 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 23.8 GB | 26.4 GB | 10.4 GB too big | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · Comfy-Org | 11.9 GB | 14.5 GB | fits · 1.5 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · QuantStack | 12.7 GB | 15.3 GB | fits · 0.7 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 9.8 GB | 12.4 GB | fits · 3.6 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 8.4 GB | 11.0 GB | fits · 5.0 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 6.9 GB | 9.5 GB | fits · 6.5 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 5.4 GB | 8.0 GB | fits · 8.0 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 4.0 GB | 6.6 GB | fits · 9.4 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 4080 Super 16 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 4080 Super 16 GB
The RTX 4080 Super 16 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.)
16 GB GDDR6X · 256-bit · 736 GB/s · Ada Lovelace. Everything that runs on it →
05Questions
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 4080 Super 16 GB?
FP8 (11.9 GB) from Comfy-Org/flux1-kontext-dev_ComfyUI.
FP8 or Q8_0 for FLUX.1 Kontext on the RTX 4080 Super 16 GB?
FP8 (11.9 GB): the RTX 4080 Super 16 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 4080 Super 16 GB?
17.4 GB: flux1-dev-kontext_fp8_scaled.safetensors, t5xxl_fp8_e4m3fn.safetensors, clip_l.safetensors, ae.safetensors.