LLaVA 1.6 13B on NVIDIA GeForce RTX 4090
NVIDIA GeForce RTX 4090 handles LLaVA 1.6 13B well at 30 tok/s at Q5_K_M. A solid choice for this model.
Model Size
13B
Device VRAM
24 GB
Bandwidth
1008 GB/s
Quantizations Tested
1
Performance by Quantization
Each row shows LLaVA 1.6 13B performance at a different quality level on NVIDIA GeForce RTX 4090.
| 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 — 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
Source: Multimodal model reports (2026-01-15)
Data last updated: 2026-03-01