Can the RTX 5070 12 GB run FLUX.2 [klein] 9B?
Yes, but only just: FP8 leaves 0.3 GB free on the RTX 5070 12 GB.
FP8 (9.4 GB) fits with only 0.3 GB to spare (about 11.7 GB of 12 GB).
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux-2-klein-9b-fp8.safetensors FP8 · black-forest-labs/FLUX.2-klein-9b-fp8 | models/diffusion_models | 9.4 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 | 18.4 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 →
02Every FLUX.2 klein 9B file on 12 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 18.2 GB | 20.5 GB | 8.5 GB too big | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · black-forest-labs | 9.4 GB | 11.7 GB | fits · 0.3 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · unsloth | 10.0 GB | 12.3 GB | spills 0.3 GB | practically identical to the original | Hugging Face → |
| Q6_K GGUF · unsloth | 7.9 GB | 10.2 GB | fits · 1.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · unsloth | 7.0 GB | 9.3 GB | fits · 2.7 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · unsloth | 5.9 GB | 8.2 GB | fits · 3.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · unsloth | 4.8 GB | 7.1 GB | fits · 4.9 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · unsloth | 4.0 GB | 6.3 GB | fits · 5.7 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 5070 12 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 5070 12 GB
The RTX 5070 12 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.
12 GB GDDR7 · 192-bit · 672 GB/s · Blackwell. 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 5070 12 GB?
FP8 (9.4 GB) from black-forest-labs/FLUX.2-klein-9b-fp8.
FP8 or Q8_0 for FLUX.2 klein 9B on the RTX 5070 12 GB?
FP8 (9.4 GB): the RTX 5070 12 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 5070 12 GB?
18.4 GB: flux-2-klein-9b-fp8.safetensors, qwen_3_8b_fp8mixed.safetensors, flux2-vae.safetensors.