What is the best local model for coding on the RTX 5080?

On the RTX 5080, qwen-3.8-27b ranks first for coding in our benchmarks (86.4/100 at ~55.2 tok/s).

What is the best local model for agentic workflows on the RTX 5080?

On the RTX 5080, qwen-3.8-27b ranks first for agentic workflows in our benchmarks (91.9/100 at ~55.2 tok/s).

Hardware Benchmarks

Compare RTX 5080 benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

NVIDIA GeForce RTX 5080

Models we recommend for RTX 5080.

Fastest & Largest context

130.1 tok/sContext 204,800 tokens

Highest token generation speed at 130.1 tok/s. Largest context that fits in 16GB VRAM, at 204,800 tokens.

Best quality

27B

52.8 tok/sQuality 88.5

Highest completed quality score at 88.5.

Which models actually run best on the RTX 5080, by task, from community benchmark data.

What is the best local model for coding on the RTX 5080?: On the RTX 5080, qwen-3.8-27b ranks first for coding in our benchmarks (86.4/100 at ~55.2 tok/s).
What is the best local model for agentic workflows on the RTX 5080?: On the RTX 5080, qwen-3.8-27b ranks first for agentic workflows in our benchmarks (91.9/100 at ~55.2 tok/s).

Completed quality-ranked benchmark results for NVIDIA GeForce RTX 5080.