Can the RTX 5080 16 GB run FLUX.2 [klein] 4B?
Download 16-bit (7.8 GB). With the model's working memory it needs about 9.6 GB, leaving 6.4 GB spare on 16 GB. Quality: the original weights.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux-2-klein-4b.safetensors 16-bit · black-forest-labs/FLUX.2-klein-4B | models/diffusion_models | 7.8 GB | Download → |
| Text encoder | qwen_3_4b_fp8_mixed.safetensors Qwen3 4B FP8 · Comfy-Org/z_image_turbo | models/text_encoders | 5.6 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 | 13.7 GB | |||
Alternatives: Qwen3 4B BF16 (8.0 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.
System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 13.7 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 19.7 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated
02Every FLUX.2 klein 4B file on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · black-forest-labs | 7.8 GB | 9.6 GB | fits · 6.4 GB spare | the original weights | Hugging Face → |
| FP8 SAFETENSORS · black-forest-labs | 4.1 GB | 5.9 GB | fits · 10.1 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · unsloth | 4.3 GB | 6.1 GB | fits · 9.9 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 3.4 GB | 5.2 GB | fits · 10.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 3.1 GB | 4.9 GB | fits · 11.1 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 2.6 GB | 4.4 GB | fits · 11.6 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 2.1 GB | 3.9 GB | fits · 12.1 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 1.8 GB | 3.6 GB | fits · 12.4 GB spare | heavy loss; a last resort | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
Qwen3 4B: 8.0 GB as 16-bit, 5.6 GB as FP8. ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. On 16 GB the FP8 encoder fits on its own, so prompt encoding stays fast.
04About this GPU
The RTX 5080 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.
RTX 5080 16 GB: 16 GB GDDR7 · 256-bit · 960 GB/s · Blackwell. Everything that runs on the RTX 5080 16 GB →
05What more VRAM would change
Nothing to gain for this model: the RTX 5080 16 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.
What changes from the RTX 5080 16 GB to the RTX 5090 32 GB →
06Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run FLUX.2 klein 4B on a RTX 5080 16 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
How much VRAM does FLUX.2 klein 4B need?
Around 3.6 GB with the smallest file (Q2_K) and 5.9 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 9.6 GB.
Which FLUX.2 klein 4B file should I download for the RTX 5080 16 GB?
16-bit (7.8 GB) from black-forest-labs/FLUX.2-klein-4B.
Is FP8 faster than GGUF on the RTX 5080 16 GB?
It can be. This GPU has FP8 hardware, and ComfyUI computes FP8 natively for files made for it (Comfy-Org's fp8_scaled files), or for any FP8 file with the --fast fp8_matrix_mult option. GGUF files are unpacked on the fly, which costs some speed.
How much do I need to download for FLUX.2 klein 4B on the RTX 5080 16 GB?
About 13.7 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 16 GB card, 32 GB of system RAM or more is recommended.