What is the best local model for coding on the Pro W7900?

On the Pro W7900, Ternary-Bonsai-2-27B-PQ2_0-MTP-Q8_0 ranks first for coding in our benchmarks (78.4/100 at ~60.6 tok/s).

What is the best local model for agentic workflows on the Pro W7900?

On the Pro W7900, Ternary-Bonsai-2-27B-PQ2_0-MTP-Q8_0 ranks first for agentic workflows in our benchmarks (81.4/100 at ~60.6 tok/s).

Hardware Benchmarks

Compare Pro W7900 benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon Pro W7900

Models we recommend for Pro W7900.

Fastest & Best quality

27B

61.3 tok/sQuality 85.4

Highest token generation speed at 61.3 tok/s. Highest completed quality score at 85.4.

Which models actually run best on the Pro W7900, by task, from community benchmark data.

What is the best local model for coding on the Pro W7900?: On the Pro W7900, Ternary-Bonsai-2-27B-PQ2_0-MTP-Q8_0 ranks first for coding in our benchmarks (78.4/100 at ~60.6 tok/s).
What is the best local model for agentic workflows on the Pro W7900?: On the Pro W7900, Ternary-Bonsai-2-27B-PQ2_0-MTP-Q8_0 ranks first for agentic workflows in our benchmarks (81.4/100 at ~60.6 tok/s).

Completed quality-ranked benchmark results for AMD Radeon Pro W7900.