Can the RTX 4090 24 GB run FLUX.2 [klein] 9B?
Yes. 16-bit fits on the RTX 4090 24 GB with 3.5 GB to spare.
Take 16-bit (18.2 GB). In use it comes to about 20.5 GB, with 3.5 GB left over on 24 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux-2-klein-9b.safetensors 16-bit · black-forest-labs/FLUX.2-klein-9B | models/diffusion_models | 18.2 GB | Download → |
| Text encoder | qwen_3_8b_fp8mixed.safetensors Qwen3 8B FP8 · Comfy-Org/flux2-klein-9B | models/text_encoders | 8.7 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 | 27.2 GB | |||
Alternatives: Qwen3 8B BF16 (16.4 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: GGUF Q8_0 workflow (.json). Drag the file into ComfyUI. All workflows →
System RAM: 48 GB or more. These files take about 27.2 GB of RAM while loaded, 33.2 GB with Windows and ComfyUI. What happens with less. calculated
02Every FLUX.2 klein 9B file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · black-forest-labs | 18.2 GB | 20.5 GB | fits · 3.5 GB spare | the original weights | Hugging Face → |
| FP8 SAFETENSORS · black-forest-labs | 9.4 GB | 11.7 GB | fits · 12.3 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · unsloth | 10.0 GB | 12.3 GB | fits · 11.7 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 7.9 GB | 10.2 GB | fits · 13.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 7.0 GB | 9.3 GB | fits · 14.7 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 5.9 GB | 8.2 GB | fits · 15.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 4.8 GB | 7.1 GB | fits · 16.9 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 4.0 GB | 6.3 GB | fits · 17.7 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1.5 GB of working memory for FLUX.2 klein 9B 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.2 klein 9B on a RTX 4090 24 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 4090 24 GB
The RTX 4090 24 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.)
24 GB GDDR6X · 384-bit · 1008 GB/s · Ada Lovelace. Everything that runs on it →
05Questions
How much VRAM does FLUX.2 klein 9B need?
Around 6.3 GB with the smallest file (Q2_K) and 11.7 GB with an 8-bit file (FP8). The full 16-bit file needs about 20.5 GB.
Which FLUX.2 klein 9B file should I download for the RTX 4090 24 GB?
16-bit (18.2 GB) from black-forest-labs/FLUX.2-klein-9B.
FP8 or Q8_0 for FLUX.2 klein 9B on the RTX 4090 24 GB?
FP8 (9.4 GB): the RTX 4090 24 GB computes it natively, while Q8_0 (10.0 GB) is unpacked on the fly.
How much do I need to download for FLUX.2 klein 9B on the RTX 4090 24 GB?
27.2 GB: flux-2-klein-9b.safetensors, qwen_3_8b_fp8mixed.safetensors, flux2-vae.safetensors.