What is the best local model for coding on the 680m?

On the 680m, Qwen3.5-9B-Defiant-Fable-MTP-Q4_K_M ranks first for coding in our benchmarks (30.0/100 at ~6.0 tok/s).

What is the best local model for agentic workflows on the 680m?

On the 680m, LFM2.5-24B-A2B-Q4_K_M ranks first for agentic workflows in our benchmarks (87.6/100 at ~19.7 tok/s).

Hardware Benchmarks

Compare 680m benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon 680M

Models we recommend for 680m.

Fastest

24B

21.0 tok/s

Highest token generation speed at 21.0 tok/s.

Best quality

6.0 tok/sQuality 68.0

Highest completed quality score at 68.0.

Which models actually run best on the 680m, by task, from community benchmark data.

What is the best local model for coding on the 680m?: On the 680m, Qwen3.5-9B-Defiant-Fable-MTP-Q4_K_M ranks first for coding in our benchmarks (30.0/100 at ~6.0 tok/s).
What is the best local model for agentic workflows on the 680m?: On the 680m, LFM2.5-24B-A2B-Q4_K_M ranks first for agentic workflows in our benchmarks (87.6/100 at ~19.7 tok/s).

Completed quality-ranked benchmark results for AMD Radeon 680M.