What is the best local model for coding on the RX 6600 6600 Xt 6600m?

On the RX 6600 6600 Xt 6600m, gemma4:latest ranks first for coding in our benchmarks (54.7/100 at ~87.6 tok/s).

What is the best local model for agentic workflows on the RX 6600 6600 Xt 6600m?

On the RX 6600 6600 Xt 6600m, llama3.1:latest ranks first for agentic workflows in our benchmarks (79.4/100 at ~42.2 tok/s).

Hardware Benchmarks

Compare RX 6600 6600 Xt 6600m benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon RX 6600/6600 XT/6600M

Models we recommend for RX 6600 6600 Xt 6600m.

Fastest & Best quality & Largest context

7.5B

87.6 tok/sQuality 66.9Context 8,192 tokens

Highest token generation speed at 87.6 tok/s. Highest completed quality score at 66.9. Largest context that fits in 8GB VRAM, at 8,192 tokens.

Which models actually run best on the RX 6600 6600 Xt 6600m, by task, from community benchmark data.

What is the best local model for coding on the RX 6600 6600 Xt 6600m?: On the RX 6600 6600 Xt 6600m, gemma4:latest ranks first for coding in our benchmarks (54.7/100 at ~87.6 tok/s).
What is the best local model for agentic workflows on the RX 6600 6600 Xt 6600m?: On the RX 6600 6600 Xt 6600m, llama3.1:latest ranks first for agentic workflows in our benchmarks (79.4/100 at ~42.2 tok/s).

Completed quality-ranked benchmark results for AMD Radeon RX 6600/6600 XT/6600M.