Can the RTX 3090 24 GB run FLUX.1 Kontext [dev]?
Yes. Q8_0 fits on the RTX 3090 24 GB with 8.7 GB to spare.
Q8_0 (12.7 GB) needs about 15.3 GB in use, so 8.7 GB of the 24 GB stays free: room for a larger image, a LoRA or a ControlNet.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux1-kontext-dev-Q8_0.gguf Q8_0 · QuantStack/FLUX.1-Kontext-dev-GGUF | models/unet | 12.7 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 | 18.2 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 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 23.8 GB | 26.4 GB | 2.4 GB too big | the original weights | Hugging Face → |
| Q8_0 ← GGUF · QuantStack | 12.7 GB | 15.3 GB | fits · 8.7 GB spare | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 11.9 GB | 14.5 GB | fits · 9.5 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 9.8 GB | 12.4 GB | fits · 11.6 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 8.4 GB | 11.0 GB | fits · 13.0 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 6.9 GB | 9.5 GB | fits · 14.5 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 5.4 GB | 8.0 GB | fits · 16.0 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 4.0 GB | 6.6 GB | fits · 17.4 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 3090 24 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 3090 24 GB
The RTX 3090 24 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain - Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.
24 GB GDDR6X · 384-bit · 936 GB/s · Ampere. 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 3090 24 GB?
Q8_0 (12.7 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 3090 24 GB?
Q8_0 (12.7 GB). The RTX 3090 24 GB has no FP8 maths, so FP8 (11.9 GB) only saves memory and is a step further from the original.
How much do I need to download for FLUX.1 Kontext on the RTX 3090 24 GB?
18.2 GB: flux1-kontext-dev-Q8_0.gguf, t5xxl_fp8_e4m3fn.safetensors, clip_l.safetensors, ae.safetensors.