What is the best local model for coding on the RX 9070 Xt?

On the RX 9070 Xt, qwen3.8:27b ranks first for coding in our benchmarks (80.2/100 at ~15.0 tok/s).

What is the best local model for agentic workflows on the RX 9070 Xt?

On the RX 9070 Xt, qwen3.8-27b-gsq-rco ranks first for agentic workflows in our benchmarks (90.8/100 at ~19.3 tok/s).

Hardware Benchmarks

Compare RX 9070 Xt benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon RX 9070 XT

Models we recommend for RX 9070 Xt.

Fastest & Largest context

9.0B

85.3 tok/sContext 65,536 tokens

Highest token generation speed at 85.3 tok/s. Largest context that fits in 16GB VRAM, at 65,536 tokens.

Best quality

27B

19.3 tok/sQuality 86.0

Highest completed quality score at 86.0.

Which models actually run best on the RX 9070 Xt, by task, from community benchmark data.

What is the best local model for coding on the RX 9070 Xt?: On the RX 9070 Xt, qwen3.8:27b ranks first for coding in our benchmarks (80.2/100 at ~15.0 tok/s).
What is the best local model for agentic workflows on the RX 9070 Xt?: On the RX 9070 Xt, qwen3.8-27b-gsq-rco ranks first for agentic workflows in our benchmarks (90.8/100 at ~19.3 tok/s).

Completed quality-ranked benchmark results for AMD Radeon RX 9070 XT.