Fastest
Qwen3.8-27B-ROCMFP2
27B
Highest token generation speed at 5167.3 tok/s.
Hardware Benchmarks
Compare RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt benchmark results and see which models actually earn the best completed quality scores.
GPU-specific specifications for local LLM planning.
Models we recommend for RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt.
Fastest
27B
Highest token generation speed at 5167.3 tok/s.
Best quality
27B
Highest completed quality score at 84.5.
Largest context tested
35B
Largest context window tested on this hardware, at 262,144 tokens. Its memory wasn't measured, so this doesn't show the full window fits.
Every model the community ran on this hardware. Up is better answers, right is faster. Time to finish counts every token the model wrote, thinking included, so a model that talks a lot ends up further left.
Medians over 15 fully rated runs of 14 models. Each quantization is its own model.
Which models actually run best on the RX 6700 6700 Xt 6750 Xt 6800m 6850m Xt, by task, from community benchmark data.
Completed quality-ranked benchmark results for AMD Radeon RX 6700/6700 XT/6750 XT / 6800M/6850M XT.