Fastest
nail-qwen3.6-35b-a3b
35B
161.3 tok/s
Highest token generation speed at 161.3 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RX 9060 Xt
Compare RX 9060 Xt benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 16GB
Recommended Models
Models we recommend for RX 9060 Xt.
Best quality
ornith-1.5
Unknown
104.5 tok/sQuality 82.0
Highest completed quality score at 82.0.
Largest context
qwen3.8-27b-gsq-rco
27B
25.2 tok/sContext 16,384 tokens
Largest context that fits in 16GB VRAM, at 16,384 tokens.
Frequently asked questions
Which models actually run best on the RX 9060 Xt, by task, from community benchmark data.
- What is the best local model for coding on the RX 9060 Xt?
- On the RX 9060 Xt, qwen/qwen3.8-27b ranks first for coding in our benchmarks (80.2/100 at ~5.8 tok/s).
- What is the best local model for agentic workflows on the RX 9060 Xt?
- On the RX 9060 Xt, ornith-1.5 ranks first for agentic workflows in our benchmarks (90.3/100 at ~104.5 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for AMD Radeon RX 9060 XT.