MetaLLaVA 1.6 13B on NVIDIA GeForce RTX 4090
Yes — RTX 4090 handles LLaVA 1.6 13B well at Q5_K_M — 30 tok/s. Solid daily-driver performance on 24 GB VRAM.
Model Size
13B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantization
Q5_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for LLaVA 1.6 13B on NVIDIA GeForce RTX 4090 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 | 30 tok/s | 350ms | ✓ Yes | Good | estimated |
Notes
Q5_K_M
Q5 at 9.1GB. Good for image analysis tasks. Vision encoding adds latency.
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 GeForce RTX 4090
NVIDIA GeForce RTX 4090 has 24 GB at 1008 GB/s. Street price: $1,799.
See all models NVIDIA GeForce RTX 4090 can run →Builds with NVIDIA GeForce RTX 4090
Estimate method: Multimodal model reports. Reference hardware source: github.com (2026-01-15)
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.