What is the best local model for coding on the RTX 5060 Ti?

On the RTX 5060 Ti, gemma4:12b ranks first for coding in our benchmarks (54.5/100 at ~46.8 tok/s).

What is the best local model for agentic workflows on the RTX 5060 Ti?

On the RTX 5060 Ti, swift-qwen3.8-27b ranks first for agentic workflows in our benchmarks (92.7/100 at ~9.1 tok/s).

Hardware Benchmarks

Compare RTX 5060 Ti benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

NVIDIA GeForce RTX 5060 Ti

Models we recommend for RTX 5060 Ti.

Fastest

14.8B

224.6 tok/s

Highest token generation speed at 224.6 tok/s.

Best quality

27B

9.1 tok/sQuality 68.8

Highest completed quality score at 68.8.

Largest context

11.9B

46.8 tok/sContext 65,536 tokens

Largest context that fits in 16GB VRAM, at 65,536 tokens.

Which models actually run best on the RTX 5060 Ti, by task, from community benchmark data.

What is the best local model for coding on the RTX 5060 Ti?: On the RTX 5060 Ti, gemma4:12b ranks first for coding in our benchmarks (54.5/100 at ~46.8 tok/s).
What is the best local model for agentic workflows on the RTX 5060 Ti?: On the RTX 5060 Ti, swift-qwen3.8-27b ranks first for agentic workflows in our benchmarks (92.7/100 at ~9.1 tok/s).

Completed quality-ranked benchmark results for NVIDIA GeForce RTX 5060 Ti.