What is the best local model for coding on the 880m 890m?

On the 880m 890m, gemma4-it-e4b-FLM:latest ranks first for coding in our benchmarks (42.4/100 at ~5.8 tok/s).

What is the best local model for agentic workflows on the 880m 890m?

On the 880m 890m, qwen3.6-moe-35b-a3b-FLM:latest ranks first for agentic workflows in our benchmarks (78.6/100 at ~17.1 tok/s).

Hardware Benchmarks

Compare 880m 890m benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon 880M / 890M

Models we recommend for 880m 890m.

Fastest

35B

17.1 tok/s

Highest token generation speed at 17.1 tok/s.

Best quality

11.6 tok/sQuality 61.6

Highest completed quality score at 61.6.

Which models actually run best on the 880m 890m, by task, from community benchmark data.

What is the best local model for coding on the 880m 890m?: On the 880m 890m, gemma4-it-e4b-FLM:latest ranks first for coding in our benchmarks (42.4/100 at ~5.8 tok/s).
What is the best local model for agentic workflows on the 880m 890m?: On the 880m 890m, qwen3.6-moe-35b-a3b-FLM:latest ranks first for agentic workflows in our benchmarks (78.6/100 at ~17.1 tok/s).

Completed quality-ranked benchmark results for AMD Radeon 880M / 890M.