What is the best local model for coding on the Gtx 1660 Super?

On the Gtx 1660 Super, gemma4:latest ranks first for coding in our benchmarks (65.8/100 at ~68.3 tok/s).

What is the best local model for agentic workflows on the Gtx 1660 Super?

On the Gtx 1660 Super, llama3.1:latest ranks first for agentic workflows in our benchmarks (79.7/100 at ~26.3 tok/s).

Hardware Benchmarks

Compare Gtx 1660 Super benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

NVIDIA GeForce GTX 1660 SUPER

Models we recommend for Gtx 1660 Super.

Fastest & Best quality & Largest context

7.5B

68.3 tok/sQuality 73.2Context 8,192 tokens

Highest token generation speed at 68.3 tok/s. Highest completed quality score at 73.2. Largest context that fits in 6GB VRAM, at 8,192 tokens.

Which models actually run best on the Gtx 1660 Super, by task, from community benchmark data.

What is the best local model for coding on the Gtx 1660 Super?: On the Gtx 1660 Super, gemma4:latest ranks first for coding in our benchmarks (65.8/100 at ~68.3 tok/s).
What is the best local model for agentic workflows on the Gtx 1660 Super?: On the Gtx 1660 Super, llama3.1:latest ranks first for agentic workflows in our benchmarks (79.7/100 at ~26.3 tok/s).

Completed quality-ranked benchmark results for NVIDIA GeForce GTX 1660 SUPER.