What is the best local model for coding on the 610m + RX 9070 9070 Xt 9070 Gre?

On the 610m + RX 9070 9070 Xt 9070 Gre, cyber-tiel ranks first for coding in our benchmarks (69.4/100 at ~42.6 tok/s).

What is the best local model for agentic workflows on the 610m + RX 9070 9070 Xt 9070 Gre?

On the 610m + RX 9070 9070 Xt 9070 Gre, cyber-tiel ranks first for agentic workflows in our benchmarks (85.9/100 at ~42.6 tok/s).

Hardware Benchmarks

Compare 610m + RX 9070 9070 Xt 9070 Gre benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

AMD Radeon 610M + AMD Radeon RX 9070/9070 XT/9070 GRE

Models we recommend for 610m + RX 9070 9070 Xt 9070 Gre.

Fastest & Largest context

92.0 tok/sContext 65,536 tokens

Highest token generation speed at 92.0 tok/s. Largest context that fits in 32GB VRAM, at 65,536 tokens.

Best quality

Unknown

42.6 tok/sQuality 83.3

Highest completed quality score at 83.3.

Which models actually run best on the 610m + RX 9070 9070 Xt 9070 Gre, by task, from community benchmark data.

What is the best local model for coding on the 610m + RX 9070 9070 Xt 9070 Gre?: On the 610m + RX 9070 9070 Xt 9070 Gre, cyber-tiel ranks first for coding in our benchmarks (69.4/100 at ~42.6 tok/s).
What is the best local model for agentic workflows on the 610m + RX 9070 9070 Xt 9070 Gre?: On the 610m + RX 9070 9070 Xt 9070 Gre, cyber-tiel ranks first for agentic workflows in our benchmarks (85.9/100 at ~42.6 tok/s).

Completed quality-ranked benchmark results for AMD Radeon 610M + AMD Radeon RX 9070/9070 XT/9070 GRE.