What is the best local model for coding on the RX 6950 Xt?

On the RX 6950 Xt, qwen3.8-flash-next-iq3_xxs ranks first for coding in our benchmarks (47.2/100 at ~45.9 tok/s).

What is the best local model for agentic workflows on the RX 6950 Xt?

On the RX 6950 Xt, qwen3.8-flash-next-iq3_xxs ranks first for agentic workflows in our benchmarks (88.5/100 at ~45.9 tok/s).

Hardware Benchmarks

Compare RX 6950 Xt benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon RX 6950 XT

Models we recommend for RX 6950 Xt.

Fastest & Best quality

Unknown

52.2 tok/sQuality 85.1

Highest token generation speed at 52.2 tok/s. Highest completed quality score at 85.1.

Which models actually run best on the RX 6950 Xt, by task, from community benchmark data.

What is the best local model for coding on the RX 6950 Xt?: On the RX 6950 Xt, qwen3.8-flash-next-iq3_xxs ranks first for coding in our benchmarks (47.2/100 at ~45.9 tok/s).
What is the best local model for agentic workflows on the RX 6950 Xt?: On the RX 6950 Xt, qwen3.8-flash-next-iq3_xxs ranks first for agentic workflows in our benchmarks (88.5/100 at ~45.9 tok/s).

Completed quality-ranked benchmark results for AMD Radeon RX 6950 XT.