FLUX.2-klein-9B VRAM & GPU Requirement Calculator
Interactive hardware sizing for FLUX.2-klein-9B (9B by Black Forest Labs). Estimated 8K context footprint: 6.6 GB (INT4) • 10.4 GB (FP8) • 19.4 GB (FP16).
GPUs
Memory Requirements 10.39 GB
Requires 1 GPUs (based on memory capacity)
9 GB
All model weights
0 GB
Conversation history cache
0.78 GB
Concurrent processing cache
0.61 GB
Temporary computation cache
ComfyUI Pipeline & Hardware Estimates
Est. Gen Time
5.6 s/img
Min System RAM
32 GB RAM
Resolution
1 MP
Offload Mode
Smart Offload
Quick Deploy CLI Command
python main.py --normalvram --fp8_e4m3fn-unet --fp8_e4m3fn-text-enc --preview-method auto
Flags reflect your selected precision, context length, and tensor parallel GPU count.Open FLUX.2-klein-9B spec page →
FLUX.2-klein-9B Architecture & Memory Profile
Total Parameters
9B
Architecture
Dense Transformer
Developer / Provider
Black Forest Labs
Recommended Precision
FP8
FLUX.2-klein-9B ComfyUI VRAM Matrix by Precision & Resolution
Precomputed 3-stage ComfyUI Smart Offload + VAE Tiling VRAM peak (recommended host RAM: 32 GB).
| Precision | 1024x1024 (1MP) | 1536x1536 (2.25MP) | 2048x2048 (4MP) | LoRA Train (1MP) |
|---|---|---|---|---|
| FP16 | 19.4 GB | 20.5 GB | 22.5 GB | 23.0 GB |
| FP8 | 10.4 GB | 11.5 GB | 13.5 GB | 14.0 GB |
| INT8 | 10.4 GB | 11.5 GB | 13.5 GB | 14.0 GB |
| INT4 | 6.6 GB | 7.8 GB | 9.7 GB | 10.2 GB |
Recommended GPU Hardware for FLUX.2-klein-9B (FP8)
Minimum GPU count for 1024x1024 generation with ComfyUI offload and estimated seconds/image.
| GPU Hardware | Min GPUs | Total VRAM Pool | Est. Gen Time |
|---|---|---|---|
| NVIDIA RTX 4090 (24GB) | 1× | 24 GB | 5.6 s/img |
| NVIDIA RTX 5090 (32GB) | 1× | 32 GB | 4.1 s/img |
| Apple M4 Max (128GB) (128GB) | 1× | 128 GB | 6.8 s/img |
| NVIDIA A100 (80GB) (80GB) | 1× | 80 GB | 6 s/img |
| NVIDIA H100 (80GB) | 1× | 80 GB | 1.6 s/img |
| NVIDIA H200 (141GB) | 1× | 141 GB | 1.6 s/img |
| Huawei Ascend 910B (64GB) | 1× | 64 GB | 3.2 s/img |
FLUX.2-klein-9B Deployment FAQ
How much VRAM is needed to run FLUX.2-klein-9B?
At 1024x1024 with ComfyUI Smart Offload and VAE Tiling enabled, FLUX.2-klein-9B needs about 19.4 GB in BF16/FP16, 10.4 GB in FP8, and 6.6 GB in INT4/GGUF (paired with ~32 GB system RAM).
Can I run FLUX.2-klein-9B on RTX 4090 or H100 GPUs?
Running FLUX.2-klein-9B in FP8 precision requires at least 1x RTX 4090 (24GB) or 1x NVIDIA H100 (80GB) GPUs.
What precision should I choose for FLUX.2-klein-9B in production?
For FLUX.2-klein-9B (9B by Black Forest Labs), FP8 provides the best balance between inference speed, VRAM footprint, and output quality.