News & Updates

Qwen3.8 on one R9700: 400.7 aggregate tok/s with ROCm 10 and vLLM 0.29, plus public 200K/220K chat profiles. Benchmarks, limits and launch commands.

Run the original NEO CODER MAX GGUF in vLLM with Paiton on an R9700. Explore measured latency gains, image input and local deployment.

Paiton generates a 15-second MiniMax H3 video with stereo audio on one Radeon AI PRO R9700 in 5m 33s, with 16.7% lower latency than matched stock.

Paiton generates 1024×1024 FLUX.2 klein images in 1.054 seconds on an R9700: 16.2% lower warm latency and 33.4% lower peak Torch allocation.

Paiton serves Ornith 1.5 35B A3B at 44.63 output tok/s on one Radeon AI PRO R9700, 27% faster than tuned stock vLLM, with 21.3% lower modeled cost.