What is the best local model for coding on the RTX 4060 Ti?

On the RTX 4060 Ti, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL ranks first for coding in our benchmarks (85.4/100 at ~36.0 tok/s).

What is the best local model for agentic workflows on the RTX 4060 Ti?

On the RTX 4060 Ti, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL ranks first for agentic workflows in our benchmarks (89.4/100 at ~36.0 tok/s).

Hardware Benchmarks

Compare RTX 4060 Ti benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

NVIDIA GeForce RTX 4060 Ti

Models we recommend for RTX 4060 Ti.

Fastest

37.7 tok/s

Highest token generation speed at 37.7 tok/s.

Best quality

35B

36.0 tok/sQuality 86.4

Highest completed quality score at 86.4.

Which models actually run best on the RTX 4060 Ti, by task, from community benchmark data.

What is the best local model for coding on the RTX 4060 Ti?: On the RTX 4060 Ti, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL ranks first for coding in our benchmarks (85.4/100 at ~36.0 tok/s).
What is the best local model for agentic workflows on the RTX 4060 Ti?: On the RTX 4060 Ti, Cyber-Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL ranks first for agentic workflows in our benchmarks (89.4/100 at ~36.0 tok/s).

Completed quality-ranked benchmark results for NVIDIA GeForce RTX 4060 Ti.