community pool / model answer

Qwen3.8-27B-SSMFIX-UD-Q3_K_XL-GGUF

chat · Luis23333/Qwen3.8-27B-SSMFIX-UD-Q3_K_XL-GGUF

43.4 tok/s · model median · 1 runs in the model record.

Answer

43.4tok/s

reportedRX 9070 XT 16GB3-bit · 1 run · decodebest cell in the pool

  1. RX 9070 XT 16GB43.4 tok/sreported1 run · peak VRAM no data yet · 16 GB rig memory
Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RX 9070 XT 16GB3-bit43.4 tok/sreported430- GB8,192llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.