MetaLLaVA 1.6 13B on NVIDIA GeForce RTX 5060 8GB
RTX 5060 8GB runs LLaVA 1.6 13B at Q3_K_M — 25 tok/s due to limited memory bandwidth. Slow but functional — see all options below.
Model Size
13B
Device VRAM
8 GB
Bandwidth
448 GB/s
Quantization
Q3_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for LLaVA 1.6 13B on NVIDIA GeForce RTX 5060 8GB at Q3_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q3_K_M | 25 tok/s | 280ms | ✓ Yes | Marginal | estimated |
Notes
Q3_K_M
13B multimodal. Q3_K_M barely fits with ~1.8GB headroom. Image processing adds overhead. Estimated for rtx-5060-8gb; verify with community benchmarks.
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 5060 8GB
NVIDIA GeForce RTX 5060 8GB has 8 GB at 448 GB/s. Street price: $299.
See all models NVIDIA GeForce RTX 5060 8GB can run →Estimate method: Estimated from rtx-4060-8gb matrix rows scaled for rtx-5060-8gb memory bandwidth (Ada Gate A methodology). Reference hardware source: nvidia.com (2026-05-26)
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.