Can the RTX 2060 6 GB run FLUX.1 Kontext [dev]?
Not entirely. Even Q3_K_M is 2.0 GB over 6 GB, so ComfyUI keeps part of it in system RAM.
Nothing fits entirely, but Q3_K_M (5.4 GB) overflows by only about 2.0 GB. ComfyUI keeps that part in system RAM automatically: slower than a full fit, but usable.
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 →
01With more VRAM
With 16 GB you could run FLUX.1 Kontext at 8-bit or better (Q8_0, 12.7 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 2060 6 GB to the RTX 3060 12 GB → · What changes from the RTX 2060 6 GB to the RTX 5060 Ti 16 GB →
02Every FLUX.1 Kontext file on 6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 23.8 GB | 26.4 GB | 20.4 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 12.7 GB | 15.3 GB | 9.3 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 11.9 GB | 14.5 GB | 8.5 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 9.8 GB | 12.4 GB | 6.4 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 8.4 GB | 11.0 GB | 5.0 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 6.9 GB | 9.5 GB | 3.5 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M ← GGUF · QuantStack | 5.4 GB | 8.0 GB | spills 2.0 GB | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 4.0 GB | 6.6 GB | spills 0.6 GB | 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.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux1-kontext-dev-Q3_K_M.gguf Q3_K_M · QuantStack/FLUX.1-Kontext-dev-GGUF | models/unet | 5.4 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 | 10.8 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 →
04Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run FLUX.1 Kontext on a RTX 2060 6 GB, send your time per image and peak VRAM and it will appear here, credited.
05About the RTX 2060 6 GB
The RTX 2060 6 GB (Turing) 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.
6 GB GDDR6 · 192-bit · 336 GB/s · Turing. 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 2060 6 GB?
Q3_K_M (5.4 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 2060 6 GB?
Q8_0 (12.7 GB). The RTX 2060 6 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 2060 6 GB?
10.8 GB: flux1-kontext-dev-Q3_K_M.gguf, t5xxl_fp8_e4m3fn.safetensors, clip_l.safetensors, ae.safetensors.