Fastest
tiel-coder-35b-a3b-mtp
35B
143.7 tok/s
Highest token generation speed at 143.7 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RX 9050 9060 Xt
Compare RX 9050 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 9050 9060 Xt.
Best quality
ornith-1.5-35b-a3b-apex-mtp-i-compact
35B
40.0 tok/sQuality 85.6
Highest completed quality score at 85.6.
Largest context
ornith-1.5-9b
9B
39.2 tok/sContext 2,048,000 tokens
Largest context that fits in 16GB VRAM, at 2,048,000 tokens.
Frequently asked questions
Which models actually run best on the RX 9050 9060 Xt, by task, from community benchmark data.
- What is the best local model for coding on the RX 9050 9060 Xt?
- On the RX 9050 9060 Xt, ornith-1.5-35b-a3b-apex-mtp-i-compact ranks first for coding in our benchmarks (79.4/100 at ~40.0 tok/s).
- What is the best local model for agentic workflows on the RX 9050 9060 Xt?
- On the RX 9050 9060 Xt, ornith-1.5-35b-a3b-apex-mtp-i-compact ranks first for agentic workflows in our benchmarks (91.0/100 at ~40.0 tok/s). grm-3.2-sky-onyx is faster (~83.9 tok/s) and still scores well (86.4/100) — a good pick if you'd rather trade a little quality for speed.
Benchmark Results
Completed quality-ranked benchmark results for AMD Radeon RX 9050 / 9060 XT.