Fastest
Qwen3.8-27B-Q4_K_S
27B
39.8 tok/s
Highest token generation speed at 39.8 tok/s.
Hardware Benchmarks
Best Local LLM Performance for RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt + RX 6800 6800 Xt 6900 Xt
Compare RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt + RX 6800 6800 Xt 6900 Xt benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 30GB
- Architecture
- Multi-GPU
Recommended Models
Models we recommend for RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt + RX 6800 6800 Xt 6900 Xt.
Best quality
qwen3
Unknown
38.8 tok/sQuality 85.5
Highest completed quality score at 85.5.
Frequently asked questions
Which models actually run best on the RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt + RX 6800 6800 Xt 6900 Xt, by task, from community benchmark data.
- What is the best local model for coding on the RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt + RX 6800 6800 Xt 6900 Xt?
- On the RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt + RX 6800 6800 Xt 6900 Xt, Swift-1.5-Qwen3.8-27B-IQ4_XS ranks first for coding in our benchmarks (77.6/100 at ~38.8 tok/s).
- What is the best local model for agentic workflows on the RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt + RX 6800 6800 Xt 6900 Xt?
- On the RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt + RX 6800 6800 Xt 6900 Xt, qwen3 ranks first for agentic workflows in our benchmarks (82.8/100 at ~35.7 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for AMD Radeon RX 6700/6700 XT/6750 XT / 6800M/6850M XT + AMD Radeon RX 6800/6800 XT / 6900 XT.