What is the best local model for coding on the RX 7900 Xt?

On the RX 7900 Xt, flint:latest ranks first for coding in our benchmarks (63.3/100 at ~42.7 tok/s).

What is the best local model for agentic workflows on the RX 7900 Xt?

On the RX 7900 Xt, llama3.1:latest ranks first for agentic workflows in our benchmarks (70.5/100 at ~117.1 tok/s).

Hardware Benchmarks

Compare RX 7900 Xt benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon RX 7900 XT

Models we recommend for RX 7900 Xt.

Fastest & Best quality

7.5B

203.4 tok/sQuality 69.2

Highest token generation speed at 203.4 tok/s. Highest completed quality score at 69.2.

Largest context

39.8B

42.7 tok/sContext 65,536 tokens

Largest context that fits in 20GB VRAM, at 65,536 tokens.

Which models actually run best on the RX 7900 Xt, by task, from community benchmark data.

What is the best local model for coding on the RX 7900 Xt?: On the RX 7900 Xt, flint:latest ranks first for coding in our benchmarks (63.3/100 at ~42.7 tok/s).
What is the best local model for agentic workflows on the RX 7900 Xt?: On the RX 7900 Xt, llama3.1:latest ranks first for agentic workflows in our benchmarks (70.5/100 at ~117.1 tok/s).

Completed quality-ranked benchmark results for AMD Radeon RX 7900 XT.