What is the best local model for coding on the RTX 2080 Ti?

On the RTX 2080 Ti, unsloth/gemma-4-E4B-it-GGUF:Q4_K_M ranks first for coding in our benchmarks (50.9/100 at ~93.6 tok/s).

What is the best local model for agentic workflows on the RTX 2080 Ti?

On the RTX 2080 Ti, unsloth/gemma-4-E4B-it-GGUF:Q4_K_M ranks first for agentic workflows in our benchmarks (70.6/100 at ~93.6 tok/s).

Hardware Benchmarks

Compare RTX 2080 Ti benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

NVIDIA GeForce RTX 2080 Ti

Models we recommend for RTX 2080 Ti.

Fastest & Best quality & Largest context

94.7 tok/sQuality 62.9Context 16,384 tokens

Highest token generation speed at 94.7 tok/s. Highest completed quality score at 62.9. Largest context that fits in 11GB VRAM, at 16,384 tokens.

Which models actually run best on the RTX 2080 Ti, by task, from community benchmark data.

What is the best local model for coding on the RTX 2080 Ti?: On the RTX 2080 Ti, unsloth/gemma-4-E4B-it-GGUF:Q4_K_M ranks first for coding in our benchmarks (50.9/100 at ~93.6 tok/s).
What is the best local model for agentic workflows on the RTX 2080 Ti?: On the RTX 2080 Ti, unsloth/gemma-4-E4B-it-GGUF:Q4_K_M ranks first for agentic workflows in our benchmarks (70.6/100 at ~93.6 tok/s).

Completed quality-ranked benchmark results for NVIDIA GeForce RTX 2080 Ti.