MetaLLaVA 1.6 13B on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 runs LLaVA 1.6 13B excellently at Q5_K_M — 270 tok/s. 288 GB VRAM with plenty of headroom.
Model Size
13B
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
Q5_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for LLaVA 1.6 13B on NVIDIA Grace Blackwell Ultra GB300 at Q5_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q5_K_M | 270 tok/s | 40ms | ✓ Yes | Excellent | estimated |
Notes
Q5_K_M
Multimodal vision-language model at high quality.
About LLaVA 1.6 13B
LLaVA 1.6 13B (13B) is a chat, reasoning, multi-purpose model. Multimodal model that processes images and text together. Built on Vicuna 13B with a vision encoder. Can analyze screenshots, diagrams, and photos. Useful for builders who need to process visual content in their workflows.
View all LLaVA 1.6 13B 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.