What is the best local model for coding on the RTX 3060 Ti?

On the RTX 3060 Ti, gemma4:12b ranks first for coding in our benchmarks (65.8/100 at ~15.7 tok/s).

What is the best local model for agentic workflows on the RTX 3060 Ti?

On the RTX 3060 Ti, gemma4:e4b ranks first for agentic workflows in our benchmarks (87.1/100 at ~78.1 tok/s).

Hardware Benchmarks

Compare RTX 3060 Ti benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

NVIDIA GeForce RTX 3060 Ti

Models we recommend for RTX 3060 Ti.

Fastest

1.8B

247.5 tok/s

Highest token generation speed at 247.5 tok/s.

Best quality & Largest context

8.0B

92.6 tok/sQuality 73.9Context 8,192 tokens

Highest completed quality score at 73.9. Largest context that fits in 8GB VRAM, at 8,192 tokens.

Which models actually run best on the RTX 3060 Ti, by task, from community benchmark data.

What is the best local model for coding on the RTX 3060 Ti?: On the RTX 3060 Ti, gemma4:12b ranks first for coding in our benchmarks (65.8/100 at ~15.7 tok/s).
What is the best local model for agentic workflows on the RTX 3060 Ti?: On the RTX 3060 Ti, gemma4:e4b ranks first for agentic workflows in our benchmarks (87.1/100 at ~78.1 tok/s).

Completed quality-ranked benchmark results for NVIDIA GeForce RTX 3060 Ti.