What is the best local model for coding on the 2× RX 9070 Xt?

On the 2× RX 9070 Xt, unsloth/Qwen3.8-27B-GGUF ranks first for coding in our benchmarks (72.2/100 at ~55.5 tok/s).

What is the best local model for agentic workflows on the 2× RX 9070 Xt?

On the 2× RX 9070 Xt, unsloth/Qwen3.8-27B-GGUF ranks first for agentic workflows in our benchmarks (86.5/100 at ~55.5 tok/s).

Hardware Benchmarks

Compare 2× RX 9070 Xt benchmark results and see which models actually earn the best completed quality scores.

GPU-specific specifications for local LLM planning.

2× AMD Radeon RX 9070 XT

Models we recommend for 2× RX 9070 Xt.

Fastest & Best quality & Largest context

27B

55.5 tok/sQuality 81.7Context 8,192 tokens

Highest token generation speed at 55.5 tok/s. Highest completed quality score at 81.7. Largest context that fits in 32GB VRAM, at 8,192 tokens.

Which models actually run best on the 2× RX 9070 Xt, by task, from community benchmark data.

What is the best local model for coding on the 2× RX 9070 Xt?: On the 2× RX 9070 Xt, unsloth/Qwen3.8-27B-GGUF ranks first for coding in our benchmarks (72.2/100 at ~55.5 tok/s).
What is the best local model for agentic workflows on the 2× RX 9070 Xt?: On the 2× RX 9070 Xt, unsloth/Qwen3.8-27B-GGUF ranks first for agentic workflows in our benchmarks (86.5/100 at ~55.5 tok/s).

Completed quality-ranked benchmark results for 2× AMD Radeon RX 9070 XT.