Fastest
gemma4:latest
7.5B
85.2 tok/s
Highest token generation speed at 85.2 tok/s.
Hardware Benchmarks
Best Local LLM Performance for 8060s
Compare 8060s benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 8GB
Recommended Models
Models we recommend for 8060s.
Best quality
halogen-qwen3.8-flash-next
Unknown
66.5 tok/sQuality 85.7
Highest completed quality score at 85.7.
Largest context tested
qwen3.6:latest
35.5B
64.5 tok/sContext 131,072 tokens
Largest context window tested on this hardware, at 131,072 tokens. Its memory wasn't measured, so this doesn't show the full window fits.
Frequently asked questions
Which models actually run best on the 8060s, by task, from community benchmark data.
- What is the best local model for coding on the 8060s?
- On the 8060s, halogen-qwen3.8-flash-next ranks first for coding in our benchmarks (76.0/100 at ~66.5 tok/s).
- What is the best local model for agentic workflows on the 8060s?
- On the 8060s, halogen-qwen3.8-flash-next ranks first for agentic workflows in our benchmarks (88.4/100 at ~66.5 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for AMD Radeon 8060S.