BFLFLUX.1 Dev on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 runs FLUX.1 Dev excellently at FP16 — 15 tok/s. 288 GB VRAM with plenty of headroom.
Model Size
12B
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
FP16
Performance by Quantization
OwnRig currently has one published compatibility entry for FLUX.1 Dev on NVIDIA Grace Blackwell Ultra GB300 at FP16. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| FP16 | 15 tok/s | 100ms | ✓ Yes | Excellent | estimated |
Notes
FP16
Full FP16 quality image generation. 264GB headroom enables large batch generation.
About FLUX.1 Dev
FLUX.1 Dev (12B) is a image gen model. State-of-the-art image generation. Significantly better prompt adherence and image quality than SDXL. 12B parameter transformer model (not diffusion UNet). FP16 requires 24GB VRAM, but Q4 quantization brings it to 8GB GPUs. Non-commercial license.
View all FLUX.1 Dev hardware options →About NVIDIA Grace Blackwell Ultra GB300
NVIDIA Grace Blackwell Ultra GB300 has 288 GB at 8000 GB/s. Street price: $30,000.
See all models NVIDIA Grace Blackwell Ultra GB300 can run →Estimate method: Estimated from GB300 bandwidth ratio vs RTX 4090. Reference hardware source: dell.com (2026-03-23)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.