What is the best local model for coding on the Vega Series Vega Mobile Series?

On the Vega Series Vega Mobile Series, qwen3.5-2b ranks first for coding in our benchmarks (22.0/100 at ~22.2 tok/s).

What is the best local model for agentic workflows on the Vega Series Vega Mobile Series?

On the Vega Series Vega Mobile Series, qwen3.8-4b-distill ranks first for agentic workflows in our benchmarks (75.7/100 at ~11.0 tok/s).

Hardware Benchmarks

Compare Vega Series Vega Mobile Series benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon Vega Series / Radeon Vega Mobile Series

Models we recommend for Vega Series Vega Mobile Series.

Fastest

22.2 tok/s

Highest token generation speed at 22.2 tok/s.

Best quality

11.0 tok/sQuality 54.0

Highest completed quality score at 54.0.

Which models actually run best on the Vega Series Vega Mobile Series, by task, from community benchmark data.

What is the best local model for coding on the Vega Series Vega Mobile Series?: On the Vega Series Vega Mobile Series, qwen3.5-2b ranks first for coding in our benchmarks (22.0/100 at ~22.2 tok/s).
What is the best local model for agentic workflows on the Vega Series Vega Mobile Series?: On the Vega Series Vega Mobile Series, qwen3.8-4b-distill ranks first for agentic workflows in our benchmarks (75.7/100 at ~11.0 tok/s).

Completed quality-ranked benchmark results for AMD Radeon Vega Series / Radeon Vega Mobile Series.